github-featured/microsoft--agent-framework
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity

.NET: .NET samples: migrate coding samples to Foundry-first AIProjectClient (#6557)

Browse Source 
* Migrate 02-agents/Agents samples to AIProjectClient (Foundry)

Replace AzureOpenAIClient with AIProjectClient as the AI provider in all
02-agents/Agents samples, aligning with the Foundry-first approach.

Changes:
- 19 Program.cs files migrated to use AIProjectClient.AsAIAgent()
- 19 .csproj files updated (Azure.AI.OpenAI -> Microsoft.Agents.AI.Foundry)
- Environment variables: AZURE_OPENAI_* -> FOUNDRY_PROJECT_ENDPOINT/FOUNDRY_MODEL
- Updated description comments to reflect Foundry backend
- Provider-specific samples in AgentsWithFoundry/ intentionally unchanged

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Migrate 02-agents/AgentSkills, AgentWithMemory, AgentWithRAG, AgentOpenTelemetry to AIProjectClient

Replace AzureOpenAIClient with AIProjectClient as the AI provider.
Environment variables: AZURE_OPENAI_* -> FOUNDRY_PROJECT_ENDPOINT/FOUNDRY_MODEL.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Migrate 03-workflows samples to AIProjectClient (Foundry)

Replace AzureOpenAIClient with AIProjectClient as the AI provider in
all 03-workflows samples that use an AI model.
Environment variables: AZURE_OPENAI_* -> FOUNDRY_PROJECT_ENDPOINT/FOUNDRY_MODEL.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix PR 6557 build breaks and align Foundry client usage

- Add explicit Azure.Identity package references to migrated sample projects
  that use DefaultAzureCredential
- Fix AgentWithRAG_Step05_Neo4jGraphRAG to use AIProjectClient.AsAIAgent()
  with ChatOptions.ModelId instead of AIProjectClient.AsIChatClient()
- Keep migrated samples on AIProjectClient pattern (no FoundryAgent/AzureOpenAIClient)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR 6557 Foundry review follow-ups

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix post-rebase sample build and format regressions

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Updates to fix issues from switching to Responses.

* Fixing more tests and deleting checkpoint directories created for samples.

* Fixing formatting

* Restore DefaultAzureCredential warnings in agents samples

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Ben Thomas
2026-06-24 13:45:14 -07:00
committed by GitHub
parent 0283fd00a1
commit 336a19fd32
119 changed files with 870 additions and 1428 deletions
Download Patch File Download Diff File Expand all files Collapse all files
declarative-agents/workflow-samples/MathChat.yaml
+1 -1
View File
@@ -11,7 +11,7 @@ trigger:
kind: OnConversationStart
id: workflow_demo
actions:
- kind: InvokeAzureAgent
id: question_student
conversationId: =System.ConversationId
dotnet/agent-framework-dotnet.slnx
+6 -7
View File
@@ -1,4 +1,4 @@
<Solution>
<Solution>
<Configurations>
<BuildType Name="Debug" />
<BuildType Name="Publish" />
@@ -193,10 +193,10 @@
<File Path="samples/02-agents/AgentWithMemory/README.md" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step01_ChatHistoryMemory/AgentWithMemory_Step01_ChatHistoryMemory.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step02_MemoryUsingMem0/AgentWithMemory_Step02_MemoryUsingMem0.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step04_MemoryUsingFoundry/AgentWithMemory_Step04_MemoryUsingFoundry.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/AgentWithMemory_Step05_BoundedChatHistory.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step03_MemoryUsingValkey/AgentWithMemory_Step03_MemoryUsingValkey.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step03_MemoryUsingValkey_Bedrock/AgentWithMemory_Step03_MemoryUsingValkey_Bedrock.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step04_MemoryUsingFoundry/AgentWithMemory_Step04_MemoryUsingFoundry.csproj" />
<Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/AgentWithMemory_Step05_BoundedChatHistory.csproj" />
</Folder>
<Folder Name="/Samples/02-agents/AgentProviders/openai/">
<File Path="samples/02-agents/AgentProviders/openai/README.md" />
@@ -244,7 +244,6 @@
<Project Path="samples/03-workflows/Declarative/ConfirmInput/ConfirmInput.csproj" />
<Project Path="samples/03-workflows/Declarative/CustomerSupport/CustomerSupport.csproj" />
<Project Path="samples/03-workflows/Declarative/DeepResearch/DeepResearch.csproj" />
<Project Path="samples/03-workflows/Declarative/ExecuteCode/ExecuteCode.csproj" />
<Project Path="samples/03-workflows/Declarative/ExecuteWorkflow/ExecuteWorkflow.csproj" />
<Project Path="samples/03-workflows/Declarative/FunctionTools/FunctionTools.csproj" />
<Project Path="samples/03-workflows/Declarative/HostedWorkflow/HostedWorkflow.csproj" />
@@ -617,9 +616,9 @@
<Project Path="src/Microsoft.Agents.AI.Hosting.A2A.AspNetCore/Microsoft.Agents.AI.Hosting.A2A.AspNetCore.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting.A2A/Microsoft.Agents.AI.Hosting.A2A.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting.AspNetCore/Microsoft.Agents.AI.Hosting.AspNetCore.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting.AzureFunctions/Microsoft.Agents.AI.Hosting.AzureFunctions.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting.OpenAI/Microsoft.Agents.AI.Hosting.OpenAI.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting.AspNetCore/Microsoft.Agents.AI.Hosting.AspNetCore.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hosting/Microsoft.Agents.AI.Hosting.csproj" />
<Project Path="src/Microsoft.Agents.AI.Hyperlight/Microsoft.Agents.AI.Hyperlight.csproj" />
<Project Path="src/Microsoft.Agents.AI.LocalCodeAct/Microsoft.Agents.AI.LocalCodeAct.csproj" />
@@ -628,13 +627,13 @@
<Project Path="src/Microsoft.Agents.AI.OpenAI/Microsoft.Agents.AI.OpenAI.csproj" />
<Project Path="src/Microsoft.Agents.AI.Purview/Microsoft.Agents.AI.Purview.csproj" />
<Project Path="src/Microsoft.Agents.AI.Tools.Shell/Microsoft.Agents.AI.Tools.Shell.csproj" />
<Project Path="src/Microsoft.Agents.AI.Valkey/Microsoft.Agents.AI.Valkey.csproj" />
<Project Path="src/Microsoft.Agents.AI.Workflows.Declarative.Foundry/Microsoft.Agents.AI.Workflows.Declarative.Foundry.csproj" />
<Project Path="src/Microsoft.Agents.AI.Workflows.Declarative.Mcp/Microsoft.Agents.AI.Workflows.Declarative.Mcp.csproj" />
<Project Path="src/Microsoft.Agents.AI.Workflows.Declarative/Microsoft.Agents.AI.Workflows.Declarative.csproj" />
<Project Path="src/Microsoft.Agents.AI.Workflows.Generators/Microsoft.Agents.AI.Workflows.Generators.csproj" />
<Project Path="src/Microsoft.Agents.AI.Workflows/Microsoft.Agents.AI.Workflows.csproj" />
<Project Path="src/Microsoft.Agents.AI/Microsoft.Agents.AI.csproj" />
<Project Path="src/Microsoft.Agents.AI.Valkey/Microsoft.Agents.AI.Valkey.csproj" />
</Folder>
<Folder Name="/Tests/" />
<Folder Name="/Tests/IntegrationTests/">
@@ -685,11 +684,11 @@
<Project Path="tests/Microsoft.Agents.AI.Purview.UnitTests/Microsoft.Agents.AI.Purview.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Tools.Shell.UnitTests/Microsoft.Agents.AI.Tools.Shell.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.UnitTests/Microsoft.Agents.AI.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Valkey.UnitTests/Microsoft.Agents.AI.Valkey.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Workflows.Declarative.Mcp.UnitTests/Microsoft.Agents.AI.Workflows.Declarative.Mcp.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Workflows.Declarative.UnitTests/Microsoft.Agents.AI.Workflows.Declarative.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Workflows.Generators.UnitTests/Microsoft.Agents.AI.Workflows.Generators.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Workflows.UnitTests/Microsoft.Agents.AI.Workflows.UnitTests.csproj" />
<Project Path="tests/Microsoft.Agents.AI.Valkey.UnitTests/Microsoft.Agents.AI.Valkey.UnitTests.csproj" />
</Folder>
</Solution>
dotnet/eng/verify-samples/Program.cs
+33 -11
View File
@@ -18,13 +18,14 @@
// Note: By default, this tool expects sample build outputs to already exist.
// Pre-build the solution before running, or pass --build to avoid missing build output failures.
//
// Required environment variables (for AI-powered samples):
// AZURE_OPENAI_ENDPOINT
// AZURE_OPENAI_DEPLOYMENT_NAME (optional, defaults to gpt-5-mini)
// Required environment variables (for AI-powered verification):
// FOUNDRY_PROJECT_ENDPOINT — Your Azure AI Foundry project endpoint
// FOUNDRY_MODEL — Model deployment name (optional, defaults to gpt-5.4-mini)
using System.Diagnostics;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using VerifySamples;
var options = VerifyOptions.Parse(args);
@@ -43,14 +44,33 @@ if (!File.Exists(Path.Combine(dotnetRoot, "agent-framework-dotnet.slnx")))
}
// Set up the AI verifier
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5-mini";
var foundryEndpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT");
var foundryModel = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
OpenAI.Chat.ChatClient? chatClient = null;
if (!string.IsNullOrEmpty(endpoint))
AIAgent? verifierAgent = null;
if (!string.IsNullOrEmpty(foundryEndpoint))
{
chatClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName);
verifierAgent = new AIProjectClient(new Uri(foundryEndpoint), new DefaultAzureCredential())
.AsAIAgent(
model: foundryModel,
instructions: """
You are a test output verifier. You will be given:
1. The actual stdout output of a program
2. The stderr output (if any)
3. A list of expectations about what the output should contain or demonstrate
Your job is to determine whether the actual output satisfies each expectation.
Be reasonable — the output comes from an LLM so exact wording won't match, but the
semantic intent should be clearly satisfied.
In your response, you MUST:
- Always provide ai_reasoning with a brief overall assessment.
- Always provide exactly one entry in expectation_results for each expectation,
in the same order as the input list.
- For each expectation_results entry, echo the expectation text in the expectation
field and explain your assessment in the detail field, citing evidence from the output.
""",
name: "OutputVerifier");
}
// Set up optional log file writer
@@ -61,11 +81,13 @@ if (options.LogFilePath is not null)
await logWriter.WriteHeaderAsync();
}
Console.WriteLine($"Foundry endpoint: {foundryEndpoint ?? "(not set — AI verification disabled)"}, Model: {foundryModel}");
try
{
// Run all samples
var reporter = new ConsoleReporter();
var verifier = new SampleVerifier(chatClient);
var verifier = new SampleVerifier(verifierAgent);
var orchestrator = new VerificationOrchestrator(verifier, reporter, dotnetRoot, TimeSpan.FromMinutes(3), logWriter, buildSamples: options.BuildSamples);
var run = await orchestrator.RunAllAsync(options.Samples, options.MaxParallelism);
dotnet/eng/verify-samples/SampleVerifier.cs
+3 -26
View File
@@ -3,8 +3,6 @@
using System.ComponentModel;
using System.Text.Json.Serialization;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
namespace VerifySamples;
@@ -17,33 +15,12 @@ internal sealed class SampleVerifier
private readonly AIAgent? _verifierAgent;
/// <summary>
/// Creates a verifier. If <paramref name="chatClient"/> is provided,
/// Creates a verifier. If <paramref name="verifierAgent"/> is provided,
/// AI-based verification is available for non-deterministic samples.
/// </summary>
public SampleVerifier(ChatClient? chatClient = null)
public SampleVerifier(AIAgent? verifierAgent = null)
{
if (chatClient is not null)
{
this._verifierAgent = chatClient.AsAIAgent(
instructions: """
You are a test output verifier. You will be given:
1. The actual stdout output of a program
2. The stderr output (if any)
3. A list of expectations about what the output should contain or demonstrate
Your job is to determine whether the actual output satisfies each expectation.
Be reasonable — the output comes from an LLM so exact wording won't match, but the
semantic intent should be clearly satisfied.
In your response, you MUST:
- Always provide ai_reasoning with a brief overall assessment.
- Always provide exactly one entry in expectation_results for each expectation,
in the same order as the input list.
- For each expectation_results entry, echo the expectation text in the expectation
field and explain your assessment in the detail field, citing evidence from the output.
""",
name: "OutputVerifier");
}
this._verifierAgent = verifierAgent;
}
/// <summary>
dotnet/eng/verify-samples/WorkflowSamples.cs
+49 -59
View File
@@ -30,8 +30,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_StartHere_02_AgentsInWorkflows",
ProjectPath = "samples/03-workflows/_StartHere/02_AgentsInWorkflows",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
ExpectedOutputDescription =
[
"The output should show agent responses from a translation workflow.",
@@ -43,8 +43,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_StartHere_03_AgentWorkflowPatterns",
ProjectPath = "samples/03-workflows/_StartHere/03_AgentWorkflowPatterns",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["sequential"],
InputDelayMs = 3000,
ExpectedOutputDescription =
@@ -81,8 +81,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_StartHere_06_MixedWorkflowAgentsAndExecutors",
ProjectPath = "samples/03-workflows/_StartHere/06_MixedWorkflowAgentsAndExecutors",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["What is 2 plus 2?"],
InputDelayMs = 3000,
ExpectedOutputDescription =
@@ -96,8 +96,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_StartHere_07_WriterCriticWorkflow",
ProjectPath = "samples/03-workflows/_StartHere/07_WriterCriticWorkflow",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
MustContain = ["=== Writer-Critic Iteration Workflow ==="],
ExpectedOutputDescription =
[
@@ -115,8 +115,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Agents_CustomAgentExecutors",
ProjectPath = "samples/03-workflows/Agents/CustomAgentExecutors",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
ExpectedOutputDescription =
[
"The output should show custom workflow events including slogan generation and feedback.",
@@ -128,8 +128,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Agents_FoundryAgent",
ProjectPath = "samples/03-workflows/Agents/FoundryAgent",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
SkipReason = "Requires Azure AI Foundry project endpoint.",
},
@@ -137,8 +137,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Agents_GroupChatToolApproval",
ProjectPath = "samples/03-workflows/Agents/GroupChatToolApproval",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
MustContain = ["Starting group chat workflow for software deployment..."],
ExpectedOutputDescription =
[
@@ -153,8 +153,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Agents_WorkflowAsAnAgent",
ProjectPath = "samples/03-workflows/Agents/WorkflowAsAnAgent",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["hello", "exit"],
InputDelayMs = 5000,
ExpectedOutputDescription =
@@ -219,8 +219,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Concurrent_Concurrent",
ProjectPath = "samples/03-workflows/Concurrent/Concurrent",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
ExpectedOutputDescription =
[
"The output should show results from concurrent agent processing.",
@@ -247,8 +247,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_ConditionalEdges_01_EdgeCondition",
ProjectPath = "samples/03-workflows/ConditionalEdges/01_EdgeCondition",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
ExpectedOutputDescription =
[
"The output should show an email being classified as spam or not spam and processed accordingly.",
@@ -260,8 +260,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_ConditionalEdges_02_SwitchCase",
ProjectPath = "samples/03-workflows/ConditionalEdges/02_SwitchCase",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
ExpectedOutputDescription =
[
"The output should show an ambiguous email being classified as spam, not spam, or uncertain.",
@@ -273,8 +273,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_ConditionalEdges_03_MultiSelection",
ProjectPath = "samples/03-workflows/ConditionalEdges/03_MultiSelection",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
ExpectedOutputDescription =
[
"The output should show an email being classified and potentially routed to multiple handlers.",
@@ -371,8 +371,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Observability_WorkflowAsAnAgent",
ProjectPath = "samples/03-workflows/Observability/WorkflowAsAnAgent",
RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
SkipReason = "Interactive console with ReadLine loop; requires OTLP endpoint.",
},
@@ -384,7 +384,7 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_ConfirmInput",
ProjectPath = "samples/03-workflows/Declarative/ConfirmInput",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
Inputs = ["hello", "hello"],
InputDelayMs = 8000,
ExpectedOutputDescription = ["The output should show a confirmation prompt and a user response."],
@@ -394,8 +394,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_CustomerSupport",
ProjectPath = "samples/03-workflows/Declarative/CustomerSupport",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["My laptop won't start"],
InputDelayMs = 3000,
ExpectedOutputDescription = ["The output should show a customer support workflow processing a laptop issue, with agent responses providing troubleshooting or support."],
@@ -405,26 +405,16 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_DeepResearch",
ProjectPath = "samples/03-workflows/Declarative/DeepResearch",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
SkipReason = "Requires external weather API (wttr.in).",
},
new SampleDefinition
{
Name = "Workflow_Declarative_ExecuteCode",
ProjectPath = "samples/03-workflows/Declarative/ExecuteCode",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
Inputs = ["What is 12 * 34?"],
InputDelayMs = 5000,
ExpectedOutputDescription = ["The output should show a declarative workflow executing generated code, processing a math question and producing a result."],
},
new SampleDefinition
{
Name = "Workflow_Declarative_ExecuteWorkflow",
ProjectPath = "samples/03-workflows/Declarative/ExecuteWorkflow",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
SkipReason = "Requires a workflow file path as a CLI argument.",
},
@@ -432,8 +422,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_FunctionTools",
ProjectPath = "samples/03-workflows/Declarative/FunctionTools",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["What are today's specials?", "EXIT"],
InputDelayMs = 8000,
ExpectedOutputDescription = ["The output should show a workflow calling function tools (e.g. a menu plugin) to answer a question about restaurant specials."],
@@ -443,7 +433,7 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_HostedWorkflow",
ProjectPath = "samples/03-workflows/Declarative/HostedWorkflow",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
SkipReason = "Hosts a persistent workflow server that does not exit.",
},
@@ -451,8 +441,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_InputArguments",
ProjectPath = "samples/03-workflows/Declarative/InputArguments",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["I'd like to visit Seattle", "EXIT"],
InputDelayMs = 8000,
ExpectedOutputDescription = ["The output should show a workflow capturing location input and providing travel-related information about Seattle."],
@@ -462,8 +452,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_InvokeFunctionTool",
ProjectPath = "samples/03-workflows/Declarative/InvokeFunctionTool",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["What's the soup of the day?", "EXIT"],
InputDelayMs = 8000,
ExpectedOutputDescription = ["The output should show a workflow invoking a function tool (e.g. a menu plugin) to answer a question about the soup of the day."],
@@ -473,8 +463,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_InvokeFoundryToolboxMcp",
ProjectPath = "samples/03-workflows/Declarative/InvokeFoundryToolboxMcp",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME", "FOUNDRY_TOOLBOX_NAME", "FOUNDRY_AGENT_TOOLSET_API_VERSION"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL", "FOUNDRY_TOOLBOX_NAME", "FOUNDRY_AGENT_TOOLSET_API_VERSION"],
Inputs = ["How do I use Azure OpenAI with my data?"],
InputDelayMs = 3000,
ExpectedOutputDescription = ["The output should show a workflow using Foundry Toolbox MCP tools to search Microsoft Learn documentation and web search to provide a summary of results."],
@@ -484,8 +474,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_InvokeMcpTool",
ProjectPath = "samples/03-workflows/Declarative/InvokeMcpTool",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["Search for .NET tutorials on Microsoft Learn"],
InputDelayMs = 3000,
ExpectedOutputDescription = ["The output should show a workflow using MCP tools to search Microsoft Learn documentation and provide a summary of results."],
@@ -495,8 +485,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_Marketing",
ProjectPath = "samples/03-workflows/Declarative/Marketing",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["A smart water bottle that tracks hydration"],
InputDelayMs = 3000,
ExpectedOutputDescription = ["The output should show a marketing workflow generating content about a smart water bottle product."],
@@ -506,8 +496,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_StudentTeacher",
ProjectPath = "samples/03-workflows/Declarative/StudentTeacher",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["What is 18 + 27?"],
InputDelayMs = 3000,
ExpectedOutputDescription = ["The output should show a student-teacher workflow where a student asks a math question and a teacher provides the answer."],
@@ -517,8 +507,8 @@ internal static class WorkflowSamples
{
Name = "Workflow_Declarative_ToolApproval",
ProjectPath = "samples/03-workflows/Declarative/ToolApproval",
RequiredEnvironmentVariables = ["AZURE_AI_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
RequiredEnvironmentVariables = ["FOUNDRY_PROJECT_ENDPOINT"],
OptionalEnvironmentVariables = ["FOUNDRY_MODEL"],
Inputs = ["Search for .NET tutorials", "EXIT"],
InputDelayMs = 8000,
ExpectedOutputDescription = ["The output should show a workflow using an MCP tool with approval to search Microsoft Learn, followed by an exit from the input loop."],
dotnet/eng/verify-samples/verify-samples.csproj
+2 -3
View File
@@ -12,13 +12,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.AI.Projects" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/01-get-started/04_memory/Program.cs
+1 -2
View File
@@ -25,7 +25,7 @@ var projectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCrede
// Get the underlying IChatClient to use for the memory component.
// The memory provider needs direct IChatClient access for structured extraction.
IChatClient chatClient = projectClient
.AsAIAgent(new ChatClientAgentOptions { ChatOptions = new() { ModelId = model } })
.AsAIAgent(model: model, instructions: "You are a friendly assistant.Always address the user by their name.")
.GetService<IChatClient>()
?? throw new InvalidOperationException("Could not retrieve IChatClient from AIProjectClient agent.");
@@ -38,7 +38,6 @@ IChatClient chatClient = projectClient
// and its storage to that user id.
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new() { Instructions = "You are a friendly assistant. Always address the user by their name." },
AIContextProviders = [new UserInfoMemory(chatClient)]
});
dotnet/samples/02-agents/AgentOpenTelemetry/AgentOpenTelemetry.csproj
+2 -5
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,10 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Azure.Monitor.OpenTelemetry.Exporter" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.Extensions.Logging" />
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
<PackageReference Include="OpenAI" />
<PackageReference Include="OpenTelemetry" />
<PackageReference Include="OpenTelemetry.Exporter.Console" />
<PackageReference Include="OpenTelemetry.Exporter.OpenTelemetryProtocol" />
@@ -25,7 +22,7 @@
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
dotnet/samples/02-agents/AgentOpenTelemetry/Program.cs
+14 -15
View File
@@ -3,7 +3,7 @@
using System.ComponentModel;
using System.Diagnostics;
using System.Diagnostics.Metrics;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Azure.Monitor.OpenTelemetry.Exporter;
using Microsoft.Agents.AI;
@@ -96,8 +96,8 @@ Console.WriteLine("""
Type your message and press Enter. Type 'exit' or empty message to quit.
""");
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT environment variable is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT environment variable is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Log application startup
appLogger.LogInformation("OpenTelemetry Aspire Demo application started");
@@ -112,20 +112,19 @@ static async Task<string> GetWeatherAsync([Description("The location to get the
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
using var instrumentedChatClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsIChatClient() // Converts a native OpenAI SDK ChatClient into a Microsoft.Extensions.AI.IChatClient
.AsBuilder()
.UseFunctionInvocation()
.UseOpenTelemetry(sourceName: SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the chat client level
.Build();
appLogger.LogInformation("Creating Agent with OpenTelemetry instrumentation");
// Create the agent with the instrumented chat client
var agent = new ChatClientAgent(instrumentedChatClient,
name: "OpenTelemetryDemoAgent",
instructions: "You are a helpful assistant that provides concise and informative responses.",
tools: [AIFunctionFactory.Create(GetWeatherAsync)])
var agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(
model: deploymentName,
instructions: "You are a helpful assistant that provides concise and informative responses.",
name: "OpenTelemetryDemoAgent",
tools: [AIFunctionFactory.Create(GetWeatherAsync)],
clientFactory: client => client
.AsBuilder()
.UseFunctionInvocation()
.UseOpenTelemetry(sourceName: SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the chat client level
.Build())
.AsBuilder()
.UseOpenTelemetry(sourceName: SourceName, configure: (cfg) => cfg.EnableSensitiveData = true) // enable telemetry at the agent level
.Build();
dotnet/samples/02-agents/AgentOpenTelemetry/README.md
+16 -16
View File
@@ -1,6 +1,6 @@
# OpenTelemetry Aspire Demo with Azure OpenAI
# OpenTelemetry Aspire Demo with Microsoft Foundry
This demo showcases the integration of OpenTelemetry with the Microsoft Agent Framework using Azure OpenAI and .NET Aspire Dashboard for telemetry visualization.
This demo showcases the integration of OpenTelemetry with the Microsoft Agent Framework using Microsoft Foundry and the .NET Aspire Dashboard for telemetry visualization.
## Overview
@@ -15,7 +15,7 @@ The demo consists of three main components:
```mermaid
graph TD
A["Console App<br/>(Interactive)"] --> B["Agent Framework<br/>with OpenTel<br/>Instrumentation"]
B --> C["Azure OpenAI<br/>Service"]
B --> C["Microsoft Foundry<br/>Project"]
A --> D["Aspire Dashboard<br/>(OpenTelemetry Visualization)"]
B --> D
```
@@ -23,21 +23,21 @@ graph TD
## Prerequisites
- .NET 10 SDK or later
- Azure OpenAI service endpoint and deployment configured
- Microsoft Foundry project endpoint and model configured
- Azure CLI installed and authenticated (for Azure credential authentication)
- Docker installed (for running Aspire Dashboard)
- [Optional] Application Insights and Grafana
## Configuration
### Azure OpenAI Setup
### Microsoft Foundry Setup
Set the following environment variables:
```powershell
$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.4-mini" # Optional, defaults to gpt-5.4-mini
$env:FOUNDRY_PROJECT_ENDPOINT="https://<your-project>.services.ai.azure.com/api/projects/<your-project>"
$env:FOUNDRY_MODEL="gpt-5.4-mini" # Optional, defaults to gpt-5.4-mini
```
**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure OpenAI resource.
**Note**: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Foundry project.
### [Optional] Application Insights Setup
Set the following environment variables:
@@ -56,7 +56,7 @@ The easiest way to run the demo is using the provided PowerShell script:
```
This script will automatically:
- ✅ Check prerequisites (Docker, Azure OpenAI configuration)
- ✅ Check prerequisites (Docker, Foundry configuration)
- 🔨 Build the console application
- 🐳 Start the Aspire Dashboard via Docker (with anonymous access)
- ⏳ Wait for dashboard to be ready (polls port until listening)
@@ -124,7 +124,7 @@ You:
3. Each trace contains:
- An outer span for the entire agent interaction
- Inner spans from the Agent Framework's OpenTelemetry instrumentation
- Spans from HTTP calls to Azure OpenAI
- Spans from HTTP calls to Microsoft Foundry
### Metrics
1. Navigate to the **Metrics** tab
@@ -158,7 +158,7 @@ Open dashboard in Azure portal: <https://aka.ms/amg/dash/af-workflow>
- **Telemetry correlation** across the entire request flow
### Agent Framework Features
- **ChatClientAgent** with Azure OpenAI integration
- **ChatClientAgent** created from `AIProjectClient`
- **OpenTelemetry wrapper** using `.WithOpenTelemetry()`
- **Conversation threading** for multi-turn conversations
- **Error handling** with telemetry correlation
@@ -182,7 +182,7 @@ Complete demo startup script that handles everything automatically.
```
**Features:**
- **Automatic configuration detection** - Checks for Azure OpenAI configuration
- **Automatic configuration detection** - Checks for Foundry configuration
- **Project building** - Automatically builds projects before running
- **Error handling** - Provides clear error messages if something goes wrong
- **Multi-window support** - Opens dashboard in separate window for better experience
@@ -201,10 +201,10 @@ If you encounter port binding errors, try:
2. Or kill any processes using the conflicting ports
### Authentication Issues
- Ensure your Azure OpenAI endpoint is correctly configured
- Ensure your Foundry project endpoint is correctly configured
- Check that the environment variables are set in the correct terminal session
- Verify you're logged in with Azure CLI (`az login`) and have access to the Azure OpenAI resource
- Ensure the Azure OpenAI deployment name matches your actual deployment
- Verify you're logged in with Azure CLI (`az login`) and have access to the Foundry project
- Ensure the `FOUNDRY_MODEL` value matches an enabled model in your Foundry project
### Build Issues
- Ensure you're using .NET 10.0 SDK
@@ -216,7 +216,7 @@ If you encounter port binding errors, try:
```
AgentOpenTelemetry/
├── AgentOpenTelemetry.csproj # Project file with dependencies
├── Program.cs # Main application with Azure OpenAI agent integration
├── Program.cs # Main application with Foundry AIProjectClient agent integration
├── start-demo.ps1 # PowerShell script to start the demo
└── README.md # This file
```
dotnet/samples/02-agents/AgentProviders/azure/Agent_With_AzureOpenAIResponses/Program.cs
+1
View File
@@ -14,6 +14,7 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
// You must dissable client side conversation storage for clients that support it
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
dotnet/samples/02-agents/AgentProviders/foundry/Agent_Step09_UsingMcpClientAsTools/Program.cs
+1 -1
View File
@@ -33,7 +33,7 @@ List<AITool> agentTools = [.. mcpTools.Cast<AITool>()];
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName,
instructions: "You are a helpful assistant that can help with Microsoft documentation questions. Use the Microsoft Learn MCP tool to search for documentation.",
instructions: "You are a helpful assistant that can help with Microsoft documentation questions. Use the Microsoft Learn MCP tool to search for documentation. In the output, indicate which tool you used if any.",
name: "DocsAgent",
tools: agentTools);
dotnet/samples/02-agents/AgentProviders/foundry/Agent_Step14_CodeInterpreter/Program.cs
+31
View File
@@ -8,6 +8,7 @@ using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Assistants;
using OpenAI.Responses;
const string AgentInstructions = "You are a personal math tutor. When asked a math question, write and run code using the python tool to answer the question.";
const string AgentName = "CoderAgent-RAPI";
@@ -19,11 +20,41 @@ string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// The easiest way to add the hosted code interpreter is as follows:
/*
AIAgent agent = aiProjectClient.AsAIAgent(
deploymentName,
instructions: AgentInstructions,
name: AgentName,
tools: [new HostedCodeInterpreterTool() { Inputs = [] }]);
*/
// However, by default the reponses API does not return the output items from the hosted code interpreter tool.
// This is generally fine but for this sample we want to explicitly request those in the response generation configuration.
AIAgent agent = aiProjectClient
.GetProjectOpenAIClient()
.GetProjectResponsesClient()
.AsIChatClient(deploymentName)
.AsBuilder()
.ConfigureOptions(x =>
{
var previousFactory = x.RawRepresentationFactory;
x.RawRepresentationFactory = state =>
{
var responseOptions = previousFactory?.Invoke(state) as CreateResponseOptions ?? new CreateResponseOptions();
// Ensure that the response includes tool output items from the hosted code interpreter
responseOptions.IncludedProperties.Add(IncludedResponseProperty.CodeInterpreterCallOutputs);
return responseOptions;
};
})
.Build()
.AsAIAgent(
instructions: AgentInstructions,
name: AgentName,
tools: [new HostedCodeInterpreterTool() { Inputs = [] }]);
AgentResponse response = await agent.RunAsync("I need to solve the equation sin(x) + x^2 = 42");
dotnet/samples/02-agents/AgentSkills/Agent_Step01_FileBasedSkills/Agent_Step01_FileBasedSkills.csproj
+3 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,17 +9,13 @@
<NoWarn>$(NoWarn);MAAI001</NoWarn>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<Compile Include="..\SubprocessScriptRunner.cs" Link="SubprocessScriptRunner.cs" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<PackageReference Include="Azure.Identity" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
<!-- Copy skills directory to output -->
dotnet/samples/02-agents/AgentSkills/Agent_Step01_FileBasedSkills/Program.cs
+6 -8
View File
@@ -9,14 +9,13 @@
//
// This sample uses a unit-converter skill that converts between miles, kilometers, pounds, and kilograms.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// --- Skills Provider ---
// Discovers skills from the 'skills' directory containing SKILL.md files.
@@ -29,18 +28,17 @@ var skillsProvider = new AgentSkillsProvider(
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient()
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(new ChatClientAgentOptions
{
Name = "UnitConverterAgent",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant that can convert units.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName);
});
// --- Example: Unit conversion ---
Console.WriteLine("Converting units with file-based skills");
dotnet/samples/02-agents/AgentSkills/Agent_Step02_CodeDefinedSkills/Agent_Step02_CodeDefinedSkills.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -10,12 +10,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentSkills/Agent_Step02_CodeDefinedSkills/Program.cs
+6 -8
View File
@@ -9,14 +9,13 @@
// 3. Code scripts — executable delegates the agent can invoke directly
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// --- Build the code-defined skill ---
var unitConverterSkill = new AgentInlineSkill(
@@ -70,18 +69,17 @@ var skillsProvider = new AgentSkillsProvider(unitConverterSkill);
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient()
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(new ChatClientAgentOptions
{
Name = "UnitConverterAgent",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant that can convert units.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName);
});
// --- Example: Unit conversion ---
Console.WriteLine("Converting units with code-defined skills");
dotnet/samples/02-agents/AgentSkills/Agent_Step03_ClassBasedSkills/Agent_Step03_ClassBasedSkills.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -10,12 +10,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentSkills/Agent_Step03_ClassBasedSkills/Program.cs
+6 -8
View File
@@ -5,14 +5,13 @@
using System.ComponentModel;
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// --- Class-Based Skill ---
// Instantiate the skill class.
@@ -25,18 +24,17 @@ var skillsProvider = new AgentSkillsProvider(unitConverter);
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient()
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(new ChatClientAgentOptions
{
Name = "UnitConverterAgent",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant that can convert units.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName);
});
// --- Example: Unit conversion ---
Console.WriteLine("Converting units with class-based skills");
dotnet/samples/02-agents/AgentSkills/Agent_Step04_MixedSkills/Agent_Step04_MixedSkills.csproj
+3 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,17 +9,13 @@
<NoWarn>$(NoWarn);MAAI001;IDE0051</NoWarn>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<Compile Include="..\SubprocessScriptRunner.cs" Link="SubprocessScriptRunner.cs" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<PackageReference Include="Azure.Identity" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
<!-- Copy skills directory to output -->
dotnet/samples/02-agents/AgentSkills/Agent_Step04_MixedSkills/Program.cs
+7 -9
View File
@@ -15,15 +15,14 @@
using System.ComponentModel;
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// --- 1. Code-Defined Skill: volume-converter ---
var volumeConverterSkill = new AgentInlineSkill(
@@ -67,18 +66,17 @@ var skillsProvider = new AgentSkillsProviderBuilder()
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient()
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(new ChatClientAgentOptions
{
Name = "MultiConverterAgent",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant that can convert units, volumes, and temperatures.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName);
});
// --- Example: Use all three skills ---
Console.WriteLine("Converting with mixed skills (file + code + class)");
dotnet/samples/02-agents/AgentSkills/Agent_Step05_SkillsWithDI/Agent_Step05_SkillsWithDI.csproj
+2 -3
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -10,13 +10,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.DependencyInjection" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentSkills/Agent_Step05_SkillsWithDI/Program.cs
+5 -7
View File
@@ -15,15 +15,14 @@
using System.ComponentModel;
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.DependencyInjection;
using OpenAI.Responses;
// --- Configuration ---
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// --- DI Container ---
// Register application services that skill resources and scripts can resolve at execution time.
@@ -83,19 +82,18 @@ var skillsProvider = new AgentSkillsProvider(distanceSkill, weightSkill);
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetResponsesClient()
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(
options: new ChatClientAgentOptions
{
Name = "UnitConverterAgent",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant that can convert units.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName,
services: serviceProvider);
// --- Example: Unit conversion ---
dotnet/samples/02-agents/AgentSkills/Agent_Step06_McpBasedSkills/Agent_Step06_McpBasedSkills.csproj
+1 -2
View File
@@ -10,7 +10,6 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.Hosting" />
<PackageReference Include="ModelContextProtocol" />
@@ -18,7 +17,7 @@
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Mcp\Microsoft.Agents.AI.Mcp.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentSkills/Agent_Step06_McpBasedSkills/Program.cs
+7 -9
View File
@@ -12,7 +12,7 @@
// to discover and inject the skill into a ChatClientAgent.
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.DependencyInjection;
@@ -20,7 +20,6 @@ using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Logging;
using ModelContextProtocol.Client;
using ModelContextProtocol.Server;
using OpenAI.Responses;
if (args.Length > 0 && args[0] == "--server")
{
@@ -29,9 +28,9 @@ if (args.Length > 0 && args[0] == "--server")
}
// --- Configuration ---
string openAiEndpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
string openAiEndpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// --- MCP client + skill discovery ---
// Launch this same assembly as a stdio MCP server in a child process.
@@ -54,18 +53,17 @@ var skillsProvider = new AgentSkillsProviderBuilder()
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(new Uri(openAiEndpoint), new DefaultAzureCredential())
.GetResponsesClient()
AIAgent agent = new AIProjectClient(new Uri(openAiEndpoint), new DefaultAzureCredential())
.AsAIAgent(new ChatClientAgentOptions
{
Name = "SkillsAgent",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant. Use available skills to answer the user.",
},
AIContextProviders = [skillsProvider],
},
model: deploymentName);
});
// --- Run ---
Console.WriteLine(new string('-', 60));
dotnet/samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step01_Interpreter/AgentWithCodeAct_Step01_Interpreter.csproj
+1 -6
View File
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Hyperlight\Microsoft.Agents.AI.Hyperlight.csproj" />
</ItemGroup>
dotnet/samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step01_Interpreter/Program.cs
+5 -7
View File
@@ -4,14 +4,13 @@
// code interpreter: the model can write and execute arbitrary Python code to
// answer quantitative questions without calling any additional tools.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Hyperlight;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var guestPath = Environment.GetEnvironmentVariable("HYPERLIGHT_PYTHON_GUEST_PATH") ?? throw new InvalidOperationException("HYPERLIGHT_PYTHON_GUEST_PATH is not set.");
using var codeAct = new HyperlightCodeActProvider(HyperlightCodeActProviderOptions.CreateForWasm(guestPath));
@@ -19,13 +18,12 @@ using var codeAct = new HyperlightCodeActProvider(HyperlightCodeActProviderOptio
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new() { Instructions = "You are a helpful assistant. When the user asks something quantitative, write Python and call `execute_code` instead of guessing." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a helpful assistant. When the user asks something quantitative, write Python and call `execute_code` instead of guessing." },
AIContextProviders = [codeAct],
});
dotnet/samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step02_ToolEnabled/AgentWithCodeAct_Step02_ToolEnabled.csproj
+1 -6
View File
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Hyperlight\Microsoft.Agents.AI.Hyperlight.csproj" />
</ItemGroup>
dotnet/samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step02_ToolEnabled/Program.cs
+5 -7
View File
@@ -7,15 +7,14 @@
// ApprovalRequiredAIFunction so any code that reaches it requires user approval
// for the entire execute_code invocation.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Hyperlight;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var guestPath = Environment.GetEnvironmentVariable("HYPERLIGHT_PYTHON_GUEST_PATH") ?? throw new InvalidOperationException("HYPERLIGHT_PYTHON_GUEST_PATH is not set.");
AIFunction fetchDocs = AIFunctionFactory.Create(
@@ -42,13 +41,12 @@ using var codeAct = new HyperlightCodeActProvider(options);
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new() { Instructions = "You are a helpful assistant. Prefer orchestrating your work in a single `execute_code` block using `call_tool(...)` over issuing many direct tool calls." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a helpful assistant. Prefer orchestrating your work in a single `execute_code` block using `call_tool(...)` over issuing many direct tool calls." },
AIContextProviders = [codeAct],
});
dotnet/samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step03_ManualWiring/AgentWithCodeAct_Step03_ManualWiring.csproj
+1 -6
View File
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Hyperlight\Microsoft.Agents.AI.Hyperlight.csproj" />
</ItemGroup>
dotnet/samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step03_ManualWiring/Program.cs
+5 -7
View File
@@ -5,15 +5,14 @@
// when you want a fixed tool surface for the agent's lifetime and don't need
// the per-run snapshot/registry semantics of HyperlightCodeActProvider.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Hyperlight;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var guestPath = Environment.GetEnvironmentVariable("HYPERLIGHT_PYTHON_GUEST_PATH") ?? throw new InvalidOperationException("HYPERLIGHT_PYTHON_GUEST_PATH is not set.");
AIFunction calculate = AIFunctionFactory.Create(
@@ -34,10 +33,9 @@ var instructions =
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(instructions: instructions, tools: [executeCode]);
.AsAIAgent(model: deploymentName, instructions: instructions, tools: [executeCode]);
Console.WriteLine(await agent.RunAsync("What is 12.3 * 4.5? Use the multiply tool from within `execute_code`."));
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step01_ChatHistoryMemory/AgentWithMemory_Step01_ChatHistoryMemory.csproj
+2 -4
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,14 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step01_ChatHistoryMemory/Program.cs
+10 -11
View File
@@ -3,17 +3,18 @@
// This sample shows how to create and use a simple AI agent that stores chat messages in a vector store using the ChatHistoryMemoryProvider.
// It can then use the chat history from prior conversations to inform responses in new conversations.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
using Microsoft.SemanticKernel.Connectors.InMemory;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME") ?? "text-embedding-3-large";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("FOUNDRY_EMBEDDING_MODEL") ?? "text-embedding-3-large";
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create a vector store to store the chat messages in.
// For demonstration purposes, we are using an in-memory vector store.
@@ -23,19 +24,17 @@ VectorStore vectorStore = new InMemoryVectorStore(new InMemoryVectorStoreOptions
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
EmbeddingGenerator = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
EmbeddingGenerator = aiProjectClient
.GetProjectOpenAIClient()
.GetEmbeddingClient(embeddingDeploymentName)
.AsIEmbeddingGenerator()
});
// Create the agent and add the ChatHistoryMemoryProvider to store chat messages in the vector store.
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
AIAgent agent = aiProjectClient
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are good at telling jokes." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are good at telling jokes." },
Name = "Joker",
AIContextProviders = [new ChatHistoryMemoryProvider(
vectorStore,
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step02_MemoryUsingMem0/AgentWithMemory_Step02_MemoryUsingMem0.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Mem0\Microsoft.Agents.AI.Mem0.csproj" />
</ItemGroup>
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step02_MemoryUsingMem0/Program.cs
+7 -10
View File
@@ -6,15 +6,13 @@
using System.Net.Http.Headers;
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Mem0;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var mem0ServiceUri = Environment.GetEnvironmentVariable("MEM0_ENDPOINT") ?? throw new InvalidOperationException("MEM0_ENDPOINT is not set.");
var mem0ApiKey = Environment.GetEnvironmentVariable("MEM0_API_KEY") ?? throw new InvalidOperationException("MEM0_API_KEY is not set.");
@@ -24,16 +22,15 @@ using HttpClient mem0HttpClient = new();
mem0HttpClient.BaseAddress = new Uri(mem0ServiceUri);
mem0HttpClient.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Token", mem0ApiKey);
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
AIAgent agent = aiProjectClient
.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new() { Instructions = "You are a friendly travel assistant. Use known memories about the user when responding, and do not invent details." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a friendly travel assistant. Use known memories about the user when responding, and do not invent details." },
// The stateInitializer can be used to customize the Mem0 scope per session and it will be called each time a session
// is encountered by the Mem0Provider that does not already have Mem0Provider state stored on the session.
// If each session should have its own Mem0 scope, you can create a new id per session via the stateInitializer, e.g.:
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step03_MemoryUsingValkey/AgentWithMemory_Step03_MemoryUsingValkey.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Valkey\Microsoft.Agents.AI.Valkey.csproj" />
</ItemGroup>
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step03_MemoryUsingValkey/Program.cs
+5 -7
View File
@@ -8,16 +8,15 @@
// docker run -d --name valkey -p 6379:6379 valkey/valkey:latest
// - Azure OpenAI endpoint and deployment configured via environment variables
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Valkey;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
using Valkey.Glide;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var valkeyConnection = Environment.GetEnvironmentVariable("VALKEY_CONNECTION") ?? "localhost:6379";
var connection = await ConnectionMultiplexer.ConnectAsync(valkeyConnection);
@@ -33,11 +32,10 @@ var historyProvider = new ValkeyChatHistoryProvider(
MaxMessages = 20
});
AIAgent historyAgent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName)
AIAgent historyAgent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new() { Instructions = "You are a helpful assistant that remembers our conversation." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a helpful assistant that remembers our conversation." },
ChatHistoryProvider = historyProvider
});
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/AgentWithMemory_Step05_BoundedChatHistory.csproj
+2 -4
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,14 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/Program.cs
+9 -10
View File
@@ -5,30 +5,30 @@
// When the agent is invoked, it searches the vector store for relevant older messages and
// prepends them as a "memory" context message before the recent session history.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
using Microsoft.SemanticKernel.Connectors.InMemory;
using OpenAI.Chat;
using SampleApp;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME") ?? "text-embedding-3-large";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("FOUNDRY_EMBEDDING_MODEL") ?? "text-embedding-3-large";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var credential = new DefaultAzureCredential();
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create a vector store to store overflow chat messages.
// For demonstration purposes, we are using an in-memory vector store.
// Replace this with a persistent vector store implementation for production scenarios.
VectorStore vectorStore = new InMemoryVectorStore(new InMemoryVectorStoreOptions()
{
EmbeddingGenerator = new AzureOpenAIClient(new Uri(endpoint), credential)
EmbeddingGenerator = aiProjectClient
.GetProjectOpenAIClient()
.GetEmbeddingClient(embeddingDeploymentName)
.AsIEmbeddingGenerator()
});
@@ -49,11 +49,10 @@ var boundedProvider = new BoundedChatHistoryProvider(
searchScope: new() { UserId = "UID1" }));
// Create the agent with the bounded chat history provider.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), credential)
.GetChatClient(deploymentName)
AIAgent agent = aiProjectClient
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are a helpful assistant. Answer questions concisely." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a helpful assistant. Answer questions concisely." },
Name = "Assistant",
ChatHistoryProvider = boundedProvider,
});
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step01_BasicTextRAG/AgentWithRAG_Step01_BasicTextRAG.csproj
+2 -4
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,14 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step01_BasicTextRAG/Program.cs
+9 -11
View File
@@ -5,30 +5,29 @@
// The TextSearchProvider runs a search against the vector store via the TextSearchStore before each model invocation and injects the results into the model context.
// The TextSearchStore is a sample store implementation that hardcodes a storage schema and uses the vector store to store and retrieve documents.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Samples;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
using Microsoft.SemanticKernel.Connectors.InMemory;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME") ?? "text-embedding-3-large";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("FOUNDRY_EMBEDDING_MODEL") ?? "text-embedding-3-large";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AzureOpenAIClient azureOpenAIClient = new(
AIProjectClient aiProjectClient = new(
new Uri(endpoint),
new DefaultAzureCredential());
// Create an In-Memory vector store that uses the Azure OpenAI embedding model to generate embeddings.
// Create an In-Memory vector store that uses the Azure AI Foundry embedding model to generate embeddings.
VectorStore vectorStore = new InMemoryVectorStore(new()
{
EmbeddingGenerator = azureOpenAIClient.GetEmbeddingClient(embeddingDeploymentName).AsIEmbeddingGenerator()
EmbeddingGenerator = aiProjectClient.GetProjectOpenAIClient().GetEmbeddingClient(embeddingDeploymentName).AsIEmbeddingGenerator()
});
// Create a store that defines a storage schema, and uses the vector store to store and retrieve documents.
@@ -60,11 +59,10 @@ TextSearchProviderOptions textSearchOptions = new()
};
// Create the AI agent with the TextSearchProvider as the AI context provider.
AIAgent agent = azureOpenAIClient
.GetChatClient(deploymentName)
AIAgent agent = aiProjectClient
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
AIContextProviders = [new TextSearchProvider(SearchAdapter, textSearchOptions)],
// Since we are using ChatCompletion which stores chat history locally, we can also add a message filter
// that removes messages produced by the TextSearchProvider before they are added to the chat history, so that
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step02_CustomVectorStoreRAG/AgentWithRAG_Step02_CustomVectorStoreRAG.csproj
+1 -3
View File
@@ -9,14 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.SemanticKernel.Connectors.Qdrant" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step02_CustomVectorStoreRAG/Program.cs
+9 -11
View File
@@ -4,33 +4,32 @@
// While the sample is using Qdrant, it can easily be replaced with any other vector store that implements the Microsoft.Extensions.VectorData abstractions.
// The TextSearchProvider runs a search against the vector store before each model invocation and injects the results into the model context.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
using Microsoft.SemanticKernel.Connectors.Qdrant;
using OpenAI.Chat;
using Qdrant.Client;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME") ?? "text-embedding-3-large";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var embeddingDeploymentName = Environment.GetEnvironmentVariable("FOUNDRY_EMBEDDING_MODEL") ?? "text-embedding-3-large";
var afOverviewUrl = "https://raw.githubusercontent.com/MicrosoftDocs/semantic-kernel-docs/refs/heads/main/agent-framework/overview/index.md";
var afMigrationUrl = "https://raw.githubusercontent.com/MicrosoftDocs/semantic-kernel-docs/refs/heads/main/agent-framework/migration-guide/from-semantic-kernel/index.md";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AzureOpenAIClient azureOpenAIClient = new(
AIProjectClient aiProjectClient = new(
new Uri(endpoint),
new DefaultAzureCredential());
// Create a Qdrant vector store that uses the Azure OpenAI embedding model to generate embeddings.
// Create a Qdrant vector store that uses the Azure AI Foundry embedding model to generate embeddings.
QdrantClient client = new("localhost");
VectorStore vectorStore = new QdrantVectorStore(client, ownsClient: true, new()
{
EmbeddingGenerator = azureOpenAIClient.GetEmbeddingClient(embeddingDeploymentName).AsIEmbeddingGenerator()
EmbeddingGenerator = aiProjectClient.GetProjectOpenAIClient().GetEmbeddingClient(embeddingDeploymentName).AsIEmbeddingGenerator()
});
// Create a collection and upsert some text into it.
@@ -69,11 +68,10 @@ TextSearchProviderOptions textSearchOptions = new()
};
// Create the AI agent with the TextSearchProvider as the AI context provider.
AIAgent agent = azureOpenAIClient
.GetChatClient(deploymentName)
AIAgent agent = aiProjectClient
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are a helpful support specialist for the Microsoft Agent Framework. Answer questions using the provided context and cite the source document when available. Keep responses brief." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a helpful support specialist for the Microsoft Agent Framework. Answer questions using the provided context and cite the source document when available. Keep responses brief." },
AIContextProviders = [new TextSearchProvider(SearchAdapter, textSearchOptions)],
// Configure a filter on the InMemoryChatHistoryProvider so that we don't persist the messages produced by the TextSearchProvider in chat history.
// The default is to persist all messages except those that came from chat history in the first place.
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step03_CustomRAGDataSource/AgentWithRAG_Step03_CustomRAGDataSource.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step03_CustomRAGDataSource/Program.cs
+5 -7
View File
@@ -6,14 +6,13 @@
// The provider invokes the custom search function
// before each model invocation and injects the results into the model context.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
TextSearchProviderOptions textSearchOptions = new()
{
@@ -25,13 +24,12 @@ TextSearchProviderOptions textSearchOptions = new()
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
AIContextProviders = [new TextSearchProvider(MockSearchAsync, textSearchOptions)]
});
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step05_Neo4jGraphRAG/AgentWithRAG_Step05_Neo4jGraphRAG.csproj
+3 -5
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -20,15 +20,13 @@
</ItemGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" Version="2.9.0-beta.1" />
<PackageReference Include="Azure.Identity" Version="1.19.0" />
<PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-rc4" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.6.0" />
<PackageReference Include="Microsoft.Agents.AI.Foundry" Version="1.2.0" />
<PackageReference Include="Neo4j.AgentFramework.GraphRAG" Version="0.1.0-preview.2" />
<PackageReference Include="Neo4j.Driver" Version="5.28.0" />
</ItemGroup>
<ItemGroup>
<PackageReference Include="Azure.Identity" Version="1.21.0" />
<PackageReference Include="Microsoft.CodeAnalysis.NetAnalyzers" Version="10.0.100">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
dotnet/samples/02-agents/AgentWithRAG/AgentWithRAG_Step05_Neo4jGraphRAG/Program.cs
+5 -6
View File
@@ -1,14 +1,14 @@
// Copyright (c) Microsoft. All rights reserved.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Neo4j.AgentFramework.GraphRAG;
using Neo4j.Driver;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var neo4jUri = Environment.GetEnvironmentVariable("NEO4J_URI") ?? throw new InvalidOperationException("NEO4J_URI is not set.");
var neo4jUsername = Environment.GetEnvironmentVariable("NEO4J_USERNAME") ?? "neo4j";
var neo4jPassword = Environment.GetEnvironmentVariable("NEO4J_PASSWORD") ?? throw new InvalidOperationException("NEO4J_PASSWORD is not set.");
@@ -48,15 +48,14 @@ await using var provider = new Neo4jContextProvider(
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsIChatClient()
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant that answers questions using Neo4j graph context."
},
AIContextProviders = [provider]
dotnet/samples/02-agents/Agents/Agent_Step01_UsingFunctionToolsWithApprovals/Agent_Step01_UsingFunctionToolsWithApprovals.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step01_UsingFunctionToolsWithApprovals/Program.cs
+12 -11
View File
@@ -1,20 +1,22 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use a ChatClientAgent with function tools that require a human in the loop for approvals.
// It shows both non-streaming and streaming agent interactions using menu-related tools.
// If the agent is hosted in a service, with a remote user, combine this sample with the Persisted Conversations sample to persist the chat history
// while the agent is waiting for user input.
// Function Tools with Approvals — Human-in-the-loop tool execution
//
// This sample demonstrates how to use function tools that require human
// approval before execution. It shows both non-streaming and streaming
// agent interactions using menu-related tools.
// If the agent is hosted in a service, combine this with the Persisted
// Conversations sample to persist chat history while waiting for user input.
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
using ChatMessage = Microsoft.Extensions.AI.ChatMessage;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Create a sample function tool that the agent can use.
[Description("Get the weather for a given location.")]
@@ -26,11 +28,10 @@ static string GetWeather([Description("The location to get the weather for.")] s
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(instructions: "You are a helpful assistant", tools: [new ApprovalRequiredAIFunction(AIFunctionFactory.Create(GetWeather))]);
.AsAIAgent(model: deploymentName, instructions: "You are a helpful assistant", tools: [new ApprovalRequiredAIFunction(AIFunctionFactory.Create(GetWeather))]);
// Call the agent and check if there are any function approval requests to handle.
// For simplicity, we are assuming here that only function approvals are pending.
dotnet/samples/02-agents/Agents/Agent_Step02_StructuredOutput/Agent_Step02_StructuredOutput.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step02_StructuredOutput/Program.cs
+26 -24
View File
@@ -1,29 +1,29 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to configure ChatClientAgent to produce structured output.
// Structured Output — Configure agents to return typed JSON
//
// This sample shows how to configure a ChatClientAgent to produce
// structured output using JSON schema constraints with Azure AI Foundry.
using System.ComponentModel;
using System.Text.Json;
using System.Text.Json.Serialization;
using Azure.AI.OpenAI;
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
using SampleApp;
using ChatMessage = Microsoft.Extensions.AI.ChatMessage;
string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Create chat client to be used by chat client agents.
// Create AI Project client to be used by chat client agents.
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
ChatClient chatClient = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName);
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Demonstrates how to work with structured output via ResponseFormat with the non-generic RunAsync method.
// This approach is useful when:
@@ -31,35 +31,36 @@ ChatClient chatClient = new AzureOpenAIClient(
// and passes it as text to another agent as input, without the need for the caller to directly work with the structured output.
// b. The type of the structured output is not known at compile time, so the generic RunAsync<T> method cannot be used.
// c. The type of the structured output is represented by JSON schema only, without a corresponding class or type in the code.
await UseStructuredOutputWithResponseFormatAsync(chatClient);
await UseStructuredOutputWithResponseFormatAsync(aiProjectClient, deploymentName);
// Demonstrates how to work with structured output via the generic RunAsync<T> method.
// This approach is useful when the caller needs to directly work with the structured output in the code
// via an instance of the corresponding class or type and the type is known at compile time.
await UseStructuredOutputWithRunAsync(chatClient);
await UseStructuredOutputWithRunAsync(aiProjectClient, deploymentName);
// Demonstrates how to work with structured output when streaming using the RunStreamingAsync method.
await UseStructuredOutputWithRunStreamingAsync(chatClient);
await UseStructuredOutputWithRunStreamingAsync(aiProjectClient, deploymentName);
// Demonstrates how to add structured output support to agents that don't natively support it using the structured output middleware.
// This approach is useful when working with agents that don't support structured output natively, or agents using models
// that don't have the capability to produce structured output, allowing you to still leverage structured output features by transforming
// the text output from the agent into structured data using a chat client.
await UseStructuredOutputWithMiddlewareAsync(chatClient);
await UseStructuredOutputWithMiddlewareAsync(aiProjectClient, deploymentName);
static async Task UseStructuredOutputWithResponseFormatAsync(ChatClient chatClient)
static async Task UseStructuredOutputWithResponseFormatAsync(AIProjectClient aiProjectClient, string deploymentName)
{
Console.WriteLine("=== Structured Output with ResponseFormat ===");
// Create the agent
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions()
AIAgent agent = aiProjectClient.AsAIAgent(new ChatClientAgentOptions()
{
Name = "HelpfulAssistant",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant.",
// Specify CityInfo as the type parameter of ForJsonSchema to indicate the expected structured output from the agent.
ResponseFormat = Microsoft.Extensions.AI.ChatResponseFormat.ForJsonSchema<CityInfo>()
ResponseFormat = ChatResponseFormat.ForJsonSchema<CityInfo>()
}
});
@@ -81,12 +82,12 @@ static async Task UseStructuredOutputWithResponseFormatAsync(ChatClient chatClie
Console.WriteLine();
}
static async Task UseStructuredOutputWithRunAsync(ChatClient chatClient)
static async Task UseStructuredOutputWithRunAsync(AIProjectClient aiProjectClient, string deploymentName)
{
Console.WriteLine("=== Structured Output with RunAsync<T> ===");
// Create the agent
AIAgent agent = chatClient.AsAIAgent(name: "HelpfulAssistant", instructions: "You are a helpful assistant.");
AIAgent agent = aiProjectClient.AsAIAgent(deploymentName, name: "HelpfulAssistant", instructions: "You are a helpful assistant.");
// Set CityInfo as the type parameter of RunAsync method to specify the expected structured output from the agent and invoke it with some unstructured input.
AgentResponse<CityInfo> response = await agent.RunAsync<CityInfo>("Provide information about the capital of France.");
@@ -99,19 +100,20 @@ static async Task UseStructuredOutputWithRunAsync(ChatClient chatClient)
Console.WriteLine();
}
static async Task UseStructuredOutputWithRunStreamingAsync(ChatClient chatClient)
static async Task UseStructuredOutputWithRunStreamingAsync(AIProjectClient aiProjectClient, string deploymentName)
{
Console.WriteLine("=== Structured Output with RunStreamingAsync ===");
// Create the agent
AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions()
AIAgent agent = aiProjectClient.AsAIAgent(new ChatClientAgentOptions()
{
Name = "HelpfulAssistant",
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = "You are a helpful assistant.",
// Specify CityInfo as the type parameter of ForJsonSchema to indicate the expected structured output from the agent.
ResponseFormat = Microsoft.Extensions.AI.ChatResponseFormat.ForJsonSchema<CityInfo>()
ResponseFormat = ChatResponseFormat.ForJsonSchema<CityInfo>()
}
});
@@ -129,12 +131,12 @@ static async Task UseStructuredOutputWithRunStreamingAsync(ChatClient chatClient
Console.WriteLine();
}
static async Task UseStructuredOutputWithMiddlewareAsync(ChatClient chatClient)
static async Task UseStructuredOutputWithMiddlewareAsync(AIProjectClient aiProjectClient, string deploymentName)
{
Console.WriteLine("=== Structured Output with UseStructuredOutput Middleware ===");
// Create chat client that will transform the agent text response into structured output.
IChatClient meaiChatClient = chatClient.AsIChatClient();
IChatClient meaiChatClient = aiProjectClient.GetProjectOpenAIClient().GetProjectResponsesClientForModel(deploymentName).AsIChatClientWithStoredOutputDisabled(deploymentName);
// Create the agent
AIAgent agent = meaiChatClient.AsAIAgent(name: "HelpfulAssistant", instructions: "You are a helpful assistant.");
dotnet/samples/02-agents/Agents/Agent_Step03_PersistedConversations/Agent_Step03_PersistedConversations.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step03_PersistedConversations/Program.cs
+9 -8
View File
@@ -2,26 +2,27 @@
#pragma warning disable CA1869 // Cache and reuse 'JsonSerializerOptions' instances
// This sample shows how to create and use a simple AI agent with a conversation that can be persisted to disk.
// Persisted Conversations — Save and restore chat history to disk
//
// This sample shows how to persist an agent conversation to disk
// so it can be resumed across process restarts.
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Create the agent
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker");
.AsAIAgent(model: deploymentName, instructions: "You are good at telling jokes.", name: "Joker");
// Start a new session for the agent conversation.
AgentSession session = await agent.CreateSessionAsync();
dotnet/samples/02-agents/Agents/Agent_Step04_3rdPartyChatHistoryStorage/Agent_Step04_3rdPartyChatHistoryStorage.csproj
+2 -4
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,14 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step04_3rdPartyChatHistoryStorage/Program.cs
+15 -11
View File
@@ -2,23 +2,25 @@
#pragma warning disable CA1869 // Cache and reuse 'JsonSerializerOptions' instances
// This sample shows how to create and use a simple AI agent with custom ChatHistoryProvider that stores chat history in a custom storage location.
// The state of the custom ChatHistoryProvider (SessionDbKey) is stored in the AgentSession's StateBag, so that when the session is resumed later,
// the chat history can be retrieved from the custom storage location.
// Third-Party Chat History Storage — Custom ChatHistoryProvider
//
// This sample shows how to use a custom ChatHistoryProvider that stores
// chat history in an external location. The provider's state (SessionDbKey)
// is stored in AgentSession.StateBag so conversations can be resumed later.
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
using Microsoft.SemanticKernel.Connectors.InMemory;
using OpenAI.Chat;
using SampleApp;
using ChatMessage = Microsoft.Extensions.AI.ChatMessage;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Create a vector store to store the chat messages in.
// Replace this with a vector store implementation of your choice if you want to persist the chat history to disk.
@@ -28,16 +30,18 @@ VectorStore vectorStore = new InMemoryVectorStore();
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.GetProjectOpenAIClient()
.GetProjectResponsesClient()
.AsIChatClientWithStoredOutputDisabled(deploymentName)
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are good at telling jokes." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are good at telling jokes." },
Name = "Joker",
// Create a new ChatHistoryProvider for this agent that stores chat history in a vector store.
ChatHistoryProvider = new VectorChatHistoryProvider(vectorStore)
ChatHistoryProvider = new VectorChatHistoryProvider(vectorStore),
});
// Start a new session for the agent conversation.
dotnet/samples/02-agents/Agents/Agent_Step05_Observability/Agent_Step05_Observability.csproj
+2 -4
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,16 +9,14 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Azure.Monitor.OpenTelemetry.Exporter" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="OpenTelemetry" />
<PackageReference Include="OpenTelemetry.Exporter.Console" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step05_Observability/Program.cs
+9 -8
View File
@@ -1,17 +1,19 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create and use a simple AI agent with Azure OpenAI as the backend that logs telemetry using OpenTelemetry.
// Agent Observability — OpenTelemetry tracing with Azure AI Foundry
//
// This sample shows how to instrument an AI agent with OpenTelemetry
// for distributed tracing and telemetry logging.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Azure.Monitor.OpenTelemetry.Exporter;
using Microsoft.Agents.AI;
using OpenAI.Chat;
using OpenTelemetry;
using OpenTelemetry.Trace;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var applicationInsightsConnectionString = Environment.GetEnvironmentVariable("APPLICATIONINSIGHTS_CONNECTION_STRING");
// Create TracerProvider with console exporter
@@ -30,9 +32,8 @@ using var tracerProvider = tracerProviderBuilder.Build();
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(instructions: "You are good at telling jokes.", name: "Joker")
AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(model: deploymentName, instructions: "You are good at telling jokes.", name: "Joker")
.AsBuilder()
.UseOpenTelemetry(sourceName: sourceName)
.Build();
dotnet/samples/02-agents/Agents/Agent_Step06_DependencyInjection/Agent_Step06_DependencyInjection.csproj
+2 -4
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,14 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.Extensions.Hosting" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step06_DependencyInjection/Program.cs
+11 -19
View File
@@ -2,38 +2,30 @@
#pragma warning disable CA1812
// This sample shows how to use dependency injection to register an AIAgent and use it from a hosted service with a user input chat loop.
// Dependency Injection — Register and resolve agents via DI
//
// This sample shows how to use dependency injection to register an
// AIAgent and consume it from a hosted service with a chat loop.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Hosting;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Create a host builder that we will register services with and then run.
HostApplicationBuilder builder = Host.CreateApplicationBuilder(args);
// Add agent options to the service collection.
builder.Services.AddSingleton(new ChatClientAgentOptions() { Name = "Joker", ChatOptions = new() { Instructions = "You are good at telling jokes." } });
// Add a chat client to the service collection.
// Create the AI agent from the Azure AI Foundry project client.
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
builder.Services.AddKeyedChatClient("AzureOpenAI", (sp) => new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsIChatClient());
// Add the AI agent to the service collection.
builder.Services.AddSingleton<AIAgent>((sp) => new ChatClientAgent(
chatClient: sp.GetRequiredKeyedService<IChatClient>("AzureOpenAI"),
options: sp.GetRequiredService<ChatClientAgentOptions>()));
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
AIAgent agent = aiProjectClient.AsAIAgent(model: deploymentName, name: "Joker", instructions: "You are good at telling jokes.");
builder.Services.AddSingleton(agent);
// Add a sample service that will use the agent to respond to user input.
builder.Services.AddHostedService<SampleService>();
dotnet/samples/02-agents/Agents/Agent_Step08_UsingImages/Agent_Step08_UsingImages.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
<ItemGroup>
dotnet/samples/02-agents/Agents/Agent_Step08_UsingImages/Program.cs
+11 -10
View File
@@ -1,24 +1,25 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to use Image Multi-Modality with an AI agent.
// Using Images — Multimodal input with an AI agent
//
// This sample shows how to send image content to an AI agent
// for vision-based analysis.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
using ChatMessage = Microsoft.Extensions.AI.ChatMessage;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = System.Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = System.Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName)
var agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(
name: "VisionAgent",
instructions: "You are a helpful agent that can analyze images");
model: deploymentName,
instructions: "You are a helpful agent that can analyze images",
name: "VisionAgent");
ChatMessage message = new(ChatRole.User, [
new TextContent("What do you see in this image?"),
dotnet/samples/02-agents/Agents/Agent_Step08_UsingImages/README.md
+5 -6
View File
@@ -1,6 +1,6 @@
# Using Images with AI Agents
This sample demonstrates how to use image multi-modality with an AI agent. It shows how to create a vision-enabled agent that can analyze and describe images using Azure OpenAI.
This sample demonstrates how to use image multi-modality with an AI agent. It shows how to create a vision-enabled agent that can analyze and describe images using Microsoft Foundry with `AIProjectClient`.
## What this sample demonstrates
@@ -13,13 +13,13 @@ This sample demonstrates how to use image multi-modality with an AI agent. It sh
- **Vision Agent**: Creates an agent specifically instructed to analyze images
- **Multimodal Input**: Combines text questions with image uri in a single message
- **Azure OpenAI Integration**: Uses AzureOpenAI LLM agents
- **Microsoft Foundry Integration**: Uses `AIProjectClient` to create a Foundry-backed agent
## Prerequisites
Before running this sample, ensure you have:
1. An Azure OpenAI project set up
1. A Microsoft Foundry project set up
2. A compatible model deployment (e.g., gpt-5.4-mini)
3. Azure CLI installed and authenticated
@@ -28,8 +28,8 @@ Before running this sample, ensure you have:
Set the following environment variables:
```powershell
$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/" # Replace with your Azure OpenAI endpoint
$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.4-mini" # Replace with your model deployment name (optional, defaults to gpt-5.4-mini)
$env:FOUNDRY_PROJECT_ENDPOINT="https://<your-project>.services.ai.azure.com/api/projects/<your-project>" # Replace with your Foundry project endpoint
$env:FOUNDRY_MODEL="gpt-5.4-mini" # Replace with your model name (optional, defaults to gpt-5.4-mini)
```
## Run the sample
@@ -49,4 +49,3 @@ The sample will:
2. Send a message containing both text ("What do you see in this image?") and a Uri image of a green walk
3. The agent will analyze the image and provide a description
4. Clean up resources by deleting the thread and agent
dotnet/samples/02-agents/Agents/Agent_Step09_AsFunctionTool/Agent_Step09_AsFunctionTool.csproj
+2 -3
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -10,13 +10,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.Hosting" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step09_AsFunctionTool/Program.cs
+17 -15
View File
@@ -1,41 +1,43 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create and use a Azure OpenAI AI agent as a function tool.
// Agent as Function Tool — Use one agent as a tool for another
//
// This sample shows how to create an AI agent and expose it as a
// function tool that another agent can call.
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
[Description("Get the weather for a given location.")]
static string GetWeather([Description("The location to get the weather for.")] string location)
=> $"The weather in {location} is cloudy with a high of 15°C.";
// Create the chat client and agent, and provide the function tool to the agent.
// Create the agent and provide the function tool to it.
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent weatherAgent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
AIAgent weatherAgent = aiProjectClient
.AsAIAgent(
model: deploymentName,
instructions: "You answer questions about the weather.",
name: "WeatherAgent",
description: "An agent that answers questions about the weather.",
tools: [AIFunctionFactory.Create(GetWeather)]);
// Create the main agent, and provide the weather agent as a function tool.
AIAgent agent = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(instructions: "You are a helpful assistant who responds in French.", tools: [weatherAgent.AsAIFunction()]);
AIAgent agent = aiProjectClient
.AsAIAgent(
model: deploymentName,
instructions: "You are a helpful assistant who responds in French.",
tools: [weatherAgent.AsAIFunction()]);
// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("What is the weather like in Amsterdam?"));
dotnet/samples/02-agents/Agents/Agent_Step10_BackgroundResponsesWithToolsAndPersistence/Agent_Step10_BackgroundResponsesWithToolsAndPersistence.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step10_BackgroundResponsesWithToolsAndPersistence/Program.cs
+10 -9
View File
@@ -1,31 +1,32 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use background responses with ChatClientAgent and Azure OpenAI Responses for long-running operations.
// It shows polling for completion using continuation tokens, function calling during background operations,
// and persisting/restoring agent state between polling cycles.
// Background Responses with Tools — Long-running operations with persistence
//
// This sample demonstrates how to use background responses with ChatClientAgent
// for long-running operations. It shows polling for completion using continuation
// tokens, function calling during background operations, and persisting/restoring
// agent state between polling cycles.
#pragma warning disable CA1050 // Declare types in namespaces
using System.ComponentModel;
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Responses;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var stateStore = new Dictionary<string, JsonElement?>();
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient()
.AsAIAgent(
model: deploymentName,
name: "SpaceNovelWriter",
dotnet/samples/02-agents/Agents/Agent_Step11_Middleware/Agent_Step11_Middleware.csproj
+2 -3
View File
@@ -9,13 +9,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
dotnet/samples/02-agents/Agents/Agent_Step11_Middleware/Program.cs
+23 -18
View File
@@ -1,6 +1,8 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows multiple middleware layers working together with Azure OpenAI:
// Middleware — Chain multiple middleware layers on an agent
//
// This sample shows multiple middleware layers working together with Azure AI Foundry:
// chat client (global/per-request), agent run (PII filtering and guardrails),
// function invocation (logging and result overrides), human-in-the-loop
// approval workflows for sensitive function calls, and MessageAIContextProvider
@@ -8,21 +10,20 @@
using System.ComponentModel;
using System.Text.RegularExpressions;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
// Get Microsoft Foundry configuration from environment variables
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = System.Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
// Get Azure AI Foundry configuration from environment variables
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Get a client to create/retrieve server side agents with
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var azureOpenAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName);
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
[Description("Get the weather for a given location.")]
static string GetWeather([Description("The location to get the weather for.")] string location)
@@ -33,12 +34,14 @@ static string GetDateTime()
=> DateTimeOffset.Now.ToString();
// Adding middleware to the chat client level and building an agent on top of it
var originalAgent = azureOpenAIClient.AsIChatClient()
.AsBuilder()
.Use(getResponseFunc: ChatClientMiddleware, getStreamingResponseFunc: null)
.BuildAIAgent(
instructions: "You are an AI assistant that helps people find information.",
tools: [AIFunctionFactory.Create(GetDateTime, name: nameof(GetDateTime))]);
var originalAgent = aiProjectClient.AsAIAgent(
model: deploymentName,
instructions: "You are an AI assistant that helps people find information.",
tools: [AIFunctionFactory.Create(GetDateTime, name: nameof(GetDateTime))],
clientFactory: (chatClient) => chatClient
.AsBuilder()
.Use(getResponseFunc: ChatClientMiddleware, getStreamingResponseFunc: null)
.Build());
// Adding middleware to the agent level
var middlewareEnabledAgent = originalAgent
@@ -117,11 +120,13 @@ Console.WriteLine($"Context-enriched response: {contextResponse}");
// In this case we are attaching an AIContextProvider that only adds messages.
Console.WriteLine("\n\n=== Example 6: AIContextProvider on chat client pipeline ===");
var chatClientProviderAgent = azureOpenAIClient.AsIChatClient()
.AsBuilder()
.UseAIContextProviders(new DateTimeContextProvider())
.BuildAIAgent(
instructions: "You are an AI assistant that helps people find information.");
var chatClientProviderAgent = aiProjectClient.AsAIAgent(
model: deploymentName,
instructions: "You are an AI assistant that helps people find information.",
clientFactory: (chatClient) => chatClient
.AsBuilder()
.UseAIContextProviders(new DateTimeContextProvider())
.Build());
var chatClientContextResponse = await chatClientProviderAgent.RunAsync("Is it almost time for lunch?");
Console.WriteLine($"Chat client context-enriched response: {chatClientContextResponse}");
dotnet/samples/02-agents/Agents/Agent_Step11_Middleware/README.md
+3 -4
View File
@@ -7,7 +7,7 @@ This sample demonstrates how to add middleware to intercept:
## What This Sample Shows
1. Azure OpenAI integration via `AzureOpenAIClient` and `DefaultAzureCredential`
1. Microsoft Foundry integration via `AIProjectClient` and `DefaultAzureCredential`
2. Chat client middleware using `ChatClientBuilder.Use(...)`
3. Agent run middleware (PII redaction and wording guardrails)
4. Function invocation middleware (logging and overriding a tool result)
@@ -26,8 +26,8 @@ Attempting to use function middleware on agents that do not wrap a ChatClientAge
## Prerequisites
1. Environment variables:
- `AZURE_OPENAI_ENDPOINT`: Your Azure OpenAI endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: Chat deployment name (optional; defaults to `gpt-5.4-mini`)
- `FOUNDRY_PROJECT_ENDPOINT`: Your Foundry project endpoint
- `FOUNDRY_MODEL`: Model name (optional; defaults to `gpt-5.4-mini`)
2. Sign in with Azure CLI (PowerShell):
```powershell
az login
@@ -40,4 +40,3 @@ Use PowerShell:
cd dotnet/samples/02-agents/Agents/Agent_Step11_Middleware
dotnet run
```
dotnet/samples/02-agents/Agents/Agent_Step12_Plugins/Agent_Step12_Plugins.csproj
+2 -3
View File
@@ -11,13 +11,12 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Microsoft.Extensions.Logging.Console" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
dotnet/samples/02-agents/Agents/Agent_Step12_Plugins/Program.cs
+7 -6
View File
@@ -1,5 +1,7 @@
// Copyright (c) Microsoft. All rights reserved.
// Plugins — Use plugin classes with dependency injection
//
// This sample shows how to use plugins with an AI agent. Plugin classes can
// depend on other services that need to be injected. In this sample, the
// AgentPlugin class uses the WeatherProvider and CurrentTimeProvider classes
@@ -9,15 +11,14 @@
// as AI functions. The AsAITools method of the plugin class shows how to specify
// which methods should be exposed to the AI agent.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.DependencyInjection;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Create a service collection to hold the agent plugin and its dependencies.
ServiceCollection services = new();
@@ -30,11 +31,11 @@ IServiceProvider serviceProvider = services.BuildServiceProvider();
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsAIAgent(
model: deploymentName,
instructions: "You are a helpful assistant that helps people find information.",
name: "Assistant",
tools: [.. serviceProvider.GetRequiredService<AgentPlugin>().AsAITools()],
dotnet/samples/02-agents/Agents/Agent_Step13_ChatReduction/Agent_Step13_ChatReduction.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step13_ChatReduction/Program.cs
+18 -11
View File
@@ -1,30 +1,37 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to use a chat history reducer to keep the context within model size limits.
// Any implementation of Microsoft.Extensions.AI.IChatReducer can be used to customize how the chat history is reduced.
// NOTE: this feature is only supported where the chat history is stored locally, such as with OpenAI Chat Completion.
// Where the chat history is stored server side, such as with Microsoft Foundry Agents, the service must manage the chat history size.
// Chat Reduction — Keep conversation context within model limits
//
// This sample shows how to use a chat history reducer to keep the context
// within model size limits. Any IChatReducer implementation can customize
// how the chat history is reduced.
// NOTE: This feature is only supported where chat history is stored locally
// (e.g. OpenAI Chat Completion). For server-side history (e.g. Foundry Agents),
// the service manages chat history size.
using Azure.AI.OpenAI;
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Construct the agent, and provide a factory to create an in-memory chat message store with a reducer that keeps only the last 2 non-system messages.
// You must dissable client side conversation storage for clients that support it.
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.GetProjectOpenAIClient()
.GetProjectResponsesClient()
.AsIChatClientWithStoredOutputDisabled(deploymentName)
.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new() { Instructions = "You are good at telling jokes." },
ChatOptions = new() { ModelId = deploymentName, Instructions = "You are good at telling jokes." },
Name = "Joker",
ChatHistoryProvider = new InMemoryChatHistoryProvider(new() { ChatReducer = new MessageCountingChatReducer(2) })
});
dotnet/samples/02-agents/Agents/Agent_Step14_BackgroundResponses/Agent_Step14_BackgroundResponses.csproj
+1 -5
View File
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step14_BackgroundResponses/Program.cs
+9 -8
View File
@@ -1,23 +1,24 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to use background responses with ChatClientAgent and Azure OpenAI Responses.
// Background Responses — Asynchronous agent execution with polling
//
// This sample shows how to use background responses with ChatClientAgent
// and Azure AI Foundry for non-blocking agent execution.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using OpenAI.Responses;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetResponsesClient()
.AsAIAgent(model: deploymentName);
.AsAIAgent(model: deploymentName, instructions: "You are a helpful assistant.");
// Enable background responses (only supported by OpenAI Responses at this time).
AgentRunOptions options = new() { AllowBackgroundResponses = true };
dotnet/samples/02-agents/Agents/Agent_Step16_Declarative/Agent_Step16_Declarative.csproj
+1 -3
View File
@@ -9,9 +9,7 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
<PackageReference Include="Microsoft.Agents.ObjectModel" />
<PackageReference Include="Microsoft.Agents.ObjectModel.Json" />
<PackageReference Include="Microsoft.Agents.ObjectModel.PowerFx" />
@@ -19,7 +17,7 @@
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Declarative\Microsoft.Agents.AI.Declarative.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step16_Declarative/Program.cs
+9 -9
View File
@@ -1,24 +1,24 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to create an agent from a YAML based declarative representation.
// Declarative Agent — Create an agent from a YAML definition
//
// This sample shows how to create an agent from a YAML-based
// declarative representation.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Create the chat client
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
IChatClient chatClient = new AzureOpenAIClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsIChatClient();
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
IChatClient chatClient = aiProjectClient.GetProjectOpenAIClient().GetResponsesClient().AsIChatClient(deploymentName);
// Define the agent using a YAML definition.
var text =
dotnet/samples/02-agents/Agents/Agent_Step17_AdditionalAIContext/Agent_Step17_AdditionalAIContext.csproj
+1 -6
View File
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step17_AdditionalAIContext/Program.cs
+21 -16
View File
@@ -1,24 +1,26 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to inject additional AI context into a ChatClientAgent using custom AIContextProvider components that are attached to the agent.
// Multiple providers can be attached to an agent, and they will be called in sequence, each receiving the accumulated context from the previous one.
// This mechanism can be used for various purposes, such as injecting RAG search results or memories into the agent's context.
// Also note that Agent Framework already provides built-in AIContextProviders for many of these scenarios.
// Additional AI Context — Inject context via custom AIContextProviders
//
// This sample shows how to inject additional AI context into a ChatClientAgent
// using custom AIContextProvider components. Multiple providers can be attached
// and are called in sequence, each receiving accumulated context from the previous.
// This mechanism is useful for injecting RAG results, memories, or other context.
// Agent Framework also provides built-in AIContextProviders for many scenarios.
#pragma warning disable CA1869 // Cache and reuse 'JsonSerializerOptions' instances
using System.Text;
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
using SampleApp;
using MEAI = Microsoft.Extensions.AI;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// A sample function to load the next three calendar events for the user.
Func<Task<string[]>> loadNextThreeCalendarEvents = async () =>
@@ -32,17 +34,20 @@ Func<Task<string[]>> loadNextThreeCalendarEvents = async () =>
];
};
// Create an agent with an AI context provider attached that aggregates two other providers:
// Create an agent with an AI context provider attached that aggregates two other providers.
// You must dissable client side conversation storage for clients that support it:
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.GetProjectOpenAIClient()
.GetProjectResponsesClient()
.AsIChatClientWithStoredOutputDisabled(deploymentName)
.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new() { Instructions = """
ChatOptions = new() { ModelId = deploymentName, Instructions = """
You are a helpful personal assistant.
You manage a TODO list for the user. When the user has completed one of the tasks it can be removed from the TODO list. Only provide the list of TODO items if asked.
You remind users of upcoming calendar events when the user interacts with you.
@@ -120,7 +125,7 @@ namespace SampleApp
],
Messages =
[
new MEAI.ChatMessage(ChatRole.User, outputMessageBuilder.ToString())
new ChatMessage(ChatRole.User, outputMessageBuilder.ToString())
]
});
}
@@ -150,7 +155,7 @@ namespace SampleApp
/// </summary>
internal sealed class CalendarSearchAIContextProvider(Func<Task<string[]>> loadNextThreeCalendarEvents) : MessageAIContextProvider
{
protected override async ValueTask<IEnumerable<MEAI.ChatMessage>> ProvideMessagesAsync(InvokingContext context, CancellationToken cancellationToken = default)
protected override async ValueTask<IEnumerable<ChatMessage>> ProvideMessagesAsync(InvokingContext context, CancellationToken cancellationToken = default)
{
var events = await loadNextThreeCalendarEvents();
@@ -161,7 +166,7 @@ namespace SampleApp
outputMessageBuilder.AppendLine($" - {calendarEvent}");
}
return [new MEAI.ChatMessage(ChatRole.User, outputMessageBuilder.ToString())];
return [new ChatMessage(ChatRole.User, outputMessageBuilder.ToString())];
}
}
}
dotnet/samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Agent_Step18_CompactionPipeline.csproj
+2 -7
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Program.cs
+15 -13
View File
@@ -1,32 +1,34 @@
// Copyright (c) Microsoft. All rights reserved.
// This sample demonstrates how to use a CompactionProvider with a compaction pipeline
// as an AIContextProvider for an agent's in-run context management. The pipeline chains multiple
// compaction strategies from gentle to aggressive:
// 1. ToolResultCompactionStrategy - Collapses old tool-call groups into concise summaries
// 2. SummarizationCompactionStrategy - LLM-compresses older conversation spans
// 3. SlidingWindowCompactionStrategy - Keeps only the most recent N user turns
// 4. TruncationCompactionStrategy - Emergency token-budget backstop
// Compaction Pipeline — Progressive context management strategies
//
// This sample demonstrates how to use a CompactionProvider with a compaction
// pipeline as an AIContextProvider for in-run context management. The pipeline
// chains multiple compaction strategies from gentle to aggressive:
// 1. ToolResultCompactionStrategy — Collapses old tool-call groups into summaries
// 2. SummarizationCompactionStrategy — LLM-compresses older conversation spans
// 3. SlidingWindowCompactionStrategy — Keeps only the most recent N user turns
// 4. TruncationCompactionStrategy — Emergency token-budget backstop
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Compaction;
using Microsoft.Extensions.AI;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AzureOpenAIClient openAIClient = new(new Uri(endpoint), new DefaultAzureCredential());
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create a chat client for the agent and a separate one for the summarization strategy.
// Using the same model for simplicity; in production, use a smaller/cheaper model for summarization.
IChatClient agentChatClient = openAIClient.GetChatClient(deploymentName).AsIChatClient();
IChatClient summarizerChatClient = openAIClient.GetChatClient(deploymentName).AsIChatClient();
IChatClient agentChatClient = aiProjectClient.GetProjectOpenAIClient().GetResponsesClient().AsIChatClient(deploymentName);
IChatClient summarizerChatClient = aiProjectClient.GetProjectOpenAIClient().GetResponsesClient().AsIChatClient(deploymentName);
// Define a tool the agent can use, so we can see tool-result compaction in action.
[Description("Look up the current price of a product by name.")]
dotnet/samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing/Agent_Step19_InFunctionLoopCheckpointing.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing/Program.cs
+11 -8
View File
@@ -1,5 +1,7 @@
// Copyright (c) Microsoft. All rights reserved.
// In-Function Loop Checkpointing — Persist chat history per service call
//
// This sample demonstrates how the ChatClientAgent persists chat history after each individual
// call to the AI service, using the RequirePerServiceCallChatHistoryPersistence option.
// When an agent uses tools, FunctionInvokingChatClient may loop multiple times
@@ -21,20 +23,20 @@
// using streaming (RunStreamingAsync), to demonstrate correct behavior in both modes.
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
using OpenAI.Responses;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var store = Environment.GetEnvironmentVariable("AZURE_OPENAI_RESPONSES_STORE") ?? "false";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
var store = Environment.GetEnvironmentVariable("FOUNDRY_RESPONSES_STORE") ?? "false";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AzureOpenAIClient openAIClient = new(new Uri(endpoint), new DefaultAzureCredential());
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Define multiple tools so the model makes several tool calls in a single run.
[Description("Get the current weather for a city.")]
@@ -93,9 +95,10 @@ static string CheckTravelAdvisory([Description("The city name.")] string city)
// Create the agent — per-service-call persistence is enabled via RequirePerServiceCallChatHistoryPersistence.
// The in-memory ChatHistoryProvider is used by default when the service does not require service stored chat
// history, so for those cases, we can inspect the chat history via session.TryGetInMemoryChatHistory().
var responsesClient = aiProjectClient.GetProjectOpenAIClient().GetProjectResponsesClientForModel(deploymentName);
IChatClient chatClient = string.Equals(store, "TRUE", StringComparison.OrdinalIgnoreCase) ?
openAIClient.GetResponsesClient().AsIChatClient(deploymentName) :
openAIClient.GetResponsesClient().AsIChatClientWithStoredOutputDisabled(deploymentName);
responsesClient.AsIChatClient(deploymentName) :
responsesClient.AsIChatClientWithStoredOutputDisabled(deploymentName);
AIAgent agent = chatClient.AsAIAgent(
new ChatClientAgentOptions
{
dotnet/samples/02-agents/Agents/Agent_Step20_DynamicFunctionTools/Agent_Step20_DynamicFunctionTools.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
</ItemGroup>
</Project>
dotnet/samples/02-agents/Agents/Agent_Step20_DynamicFunctionTools/Program.cs
+11 -10
View File
@@ -7,13 +7,13 @@
// can then use the newly added tools in subsequent iterations of the same function-calling loop.
using System.ComponentModel;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// Pre-defined tool implementations that can be loaded on demand.
[Description("Get the current weather for a city.")]
@@ -97,20 +97,21 @@ AIFunction requestToolsFunction = AIFunctionFactory.Create(
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
AIAgent agent = new AzureOpenAIClient(
AIAgent agent = new AIProjectClient(
new Uri(endpoint),
new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsIChatClient()
.AsBuilder()
.Use(getResponseFunc: ToolLoggingMiddleware, getStreamingResponseFunc: ToolLoggingStreamingMiddleware)
.BuildAIAgent(
.AsAIAgent(
model: deploymentName,
instructions: """
You are a helpful assistant. You start with limited tools.
When you need functionality that you don't currently have, call RequestTools with a description
of what you need. After new tools are loaded, use them to answer the user's question.
""",
tools: [requestToolsFunction]);
tools: [requestToolsFunction],
clientFactory: (chatClient) => chatClient
.AsBuilder()
.Use(getResponseFunc: ToolLoggingMiddleware, getStreamingResponseFunc: ToolLoggingStreamingMiddleware)
.Build());
// Run a conversation that triggers dynamic tool expansion.
Console.WriteLine("=== Dynamic Function Tools Sample ===\n");
dotnet/samples/02-agents/Agents/Agent_Step21_ShellWithEnvironment/Agent_Step21_ShellWithEnvironment.csproj
+1 -6
View File
@@ -9,13 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Tools.Shell\Microsoft.Agents.AI.Tools.Shell.csproj" />
</ItemGroup>
dotnet/samples/02-agents/Agents/Agent_Step21_ShellWithEnvironment/Program.cs
+8 -8
View File
@@ -30,21 +30,19 @@
// (cd into a folder and run a sequence of commands there; set a
// token in one step and read it in the next).
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Tools.Shell;
using Microsoft.Extensions.AI;
using OpenAI.Chat;
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var chatClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName);
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
const string Instructions = """
You are an agent with a single tool: run_shell. Use it to satisfy the
@@ -59,10 +57,11 @@ Console.WriteLine("### Stateless mode\n");
await using (var statelessShell = new LocalShellExecutor(new() { Mode = ShellMode.Stateless, AcknowledgeUnsafe = true }))
{
var envProvider = new ShellEnvironmentProvider(statelessShell);
var statelessAgent = chatClient.AsAIAgent(new ChatClientAgentOptions
var statelessAgent = aiProjectClient.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = Instructions,
Tools = [statelessShell.AsAIFunction(requireApproval: false)],
},
@@ -91,10 +90,11 @@ Console.WriteLine("\n### Persistent mode\n");
await using (var persistentShell = new LocalShellExecutor(new() { Mode = ShellMode.Persistent, AcknowledgeUnsafe = true }))
{
var envProvider = new ShellEnvironmentProvider(persistentShell);
var persistentAgent = chatClient.AsAIAgent(new ChatClientAgentOptions
var persistentAgent = aiProjectClient.AsAIAgent(new ChatClientAgentOptions
{
ChatOptions = new()
{
ModelId = deploymentName,
Instructions = Instructions,
Tools = [persistentShell.AsAIFunction(requireApproval: false)],
},
dotnet/samples/02-agents/Agents/README.md
+8 -8
View File
@@ -3,8 +3,8 @@
The getting started with agents samples demonstrate the fundamental concepts and functionalities
of single agents and can be used with any agent type.
While the functionality can be used with any agent type, these samples use Azure OpenAI as the AI provider
and use ChatCompletion as the type of service.
While the functionality can be used with any agent type, these samples are configured for
Microsoft Foundry using `AIProjectClient`.
For other samples that demonstrate how to create and configure each type of agent that come with the agent framework,
see the [How to create an agent for each provider](../AgentProviders/README.md) samples.
@@ -14,13 +14,13 @@ see the [How to create an agent for each provider](../AgentProviders/README.md)
Before you begin, ensure you have the following prerequisites:
- .NET 10 SDK or later
- Azure OpenAI service endpoint and deployment configured
- Microsoft Foundry project endpoint and model configured
- Azure CLI installed and authenticated (for Azure credential authentication)
- User has the `Cognitive Services OpenAI Contributor` role for the Azure OpenAI resource.
- User has the required role to invoke models in the Foundry project.
**Note**: These samples use Azure OpenAI models. For more information, see [how to deploy Azure OpenAI models with Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-openai).
**Note**: These samples use models hosted through Microsoft Foundry. For more information, see [Azure AI Foundry documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/).
**Note**: These samples use Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Azure OpenAI resource and have the `Cognitive Services OpenAI Contributor` role. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
**Note**: These samples use Azure CLI credentials for authentication. Make sure you're logged in with `az login` and have access to the Foundry project. For more information, see the [Azure CLI documentation](https://learn.microsoft.com/cli/azure/authenticate-azure-cli-interactively).
## Samples
@@ -59,8 +59,8 @@ cd Agent_Step01_UsingFunctionToolsWithApprovals
Set the following environment variables:
```powershell
$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/" # Replace with your Azure OpenAI resource endpoint
$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.4-mini" # Optional, defaults to gpt-5.4-mini
$env:FOUNDRY_PROJECT_ENDPOINT="https://<your-project>.services.ai.azure.com/api/projects/<your-project>" # Replace with your Foundry project endpoint
$env:FOUNDRY_MODEL="gpt-5.4-mini" # Optional, defaults to gpt-5.4-mini
```
If the variables are not set, you will be prompted for the values when running the samples.
dotnet/samples/03-workflows/Agents/CustomAgentExecutors/CustomAgentExecutors.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows.Generators\Microsoft.Agents.AI.Workflows.Generators.csproj"
OutputItemType="Analyzer"
dotnet/samples/03-workflows/Agents/CustomAgentExecutors/Program.cs
+17 -13
View File
@@ -2,7 +2,7 @@
using System.Text.Json;
using System.Text.Json.Serialization;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Workflows;
@@ -31,14 +31,14 @@ public static class Program
{
private static async Task Main()
{
// Set up the Azure OpenAI client
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var chatClient = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential()).GetChatClient(deploymentName).AsIChatClient();
// Set up the Azure AI Foundry client
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create the executors
var sloganWriter = new SloganWriterExecutor("SloganWriter", chatClient);
var feedbackProvider = new FeedbackExecutor("FeedbackProvider", chatClient);
var sloganWriter = new SloganWriterExecutor("SloganWriter", aiProjectClient, deploymentName);
var feedbackProvider = new FeedbackExecutor("FeedbackProvider", aiProjectClient, deploymentName);
// Build the workflow by adding executors and connecting them
var workflow = new WorkflowBuilder(sloganWriter)
@@ -121,19 +121,21 @@ internal sealed partial class SloganWriterExecutor : Executor
/// Initializes a new instance of the <see cref="SloganWriterExecutor"/> class.
/// </summary>
/// <param name="id">A unique identifier for the executor.</param>
/// <param name="chatClient">The chat client to use for the AI agent.</param>
public SloganWriterExecutor(string id, IChatClient chatClient) : base(id)
/// <param name="chatClient">The AI project client to use for the AI agent.</param>
/// <param name="model">The model deployment name.</param>
public SloganWriterExecutor(string id, AIProjectClient chatClient, string model) : base(id)
{
ChatClientAgentOptions agentOptions = new()
{
ChatOptions = new()
{
ModelId = model,
Instructions = "You are a professional slogan writer. You will be given a task to create a slogan.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<SloganResult>()
}
};
this._agent = new ChatClientAgent(chatClient, agentOptions);
this._agent = chatClient.AsAIAgent(agentOptions);
}
[MessageHandler]
@@ -198,19 +200,21 @@ internal sealed partial class FeedbackExecutor : Executor<SloganResult>
/// Initializes a new instance of the <see cref="FeedbackExecutor"/> class.
/// </summary>
/// <param name="id">A unique identifier for the executor.</param>
/// <param name="chatClient">The chat client to use for the AI agent.</param>
public FeedbackExecutor(string id, IChatClient chatClient) : base(id)
/// <param name="chatClient">The AI project client to use for the AI agent.</param>
/// <param name="model">The model deployment name.</param>
public FeedbackExecutor(string id, AIProjectClient chatClient, string model) : base(id)
{
ChatClientAgentOptions agentOptions = new()
{
ChatOptions = new()
{
ModelId = model,
Instructions = "You are a professional editor. You will be given a slogan and the task it is meant to accomplish.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<FeedbackResult>()
}
};
this._agent = new ChatClientAgent(chatClient, agentOptions);
this._agent = chatClient.AsAIAgent(agentOptions);
}
public override async ValueTask HandleAsync(SloganResult message, IWorkflowContext context, CancellationToken cancellationToken = default)
dotnet/samples/03-workflows/Agents/GroupChatToolApproval/GroupChatToolApproval.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
dotnet/samples/03-workflows/Agents/GroupChatToolApproval/Program.cs
+17 -18
View File
@@ -22,7 +22,7 @@
using System.ComponentModel;
using System.Text.Json;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Workflows;
@@ -42,30 +42,29 @@ public static class Program
{
private static async Task Main()
{
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
// 1. Create AI client
IChatClient client = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
.GetChatClient(deploymentName)
.AsIChatClient();
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// 2. Create specialized agents with their tools
ChatClientAgent qaEngineer = new(
client,
"You are a QA engineer responsible for running tests before deployment. Run the appropriate test suites and report results clearly.",
"QAEngineer",
"QA engineer who runs tests",
[AIFunctionFactory.Create(RunTests)]);
ChatClientAgent qaEngineer = aiProjectClient.AsAIAgent(
model: deploymentName,
instructions: "You are a QA engineer responsible for running tests before deployment. Run the appropriate test suites and report results clearly.",
name: "QAEngineer",
description: "QA engineer who runs tests",
tools: [AIFunctionFactory.Create(RunTests)]);
ChatClientAgent devopsEngineer = new(
client,
"You are a DevOps engineer responsible for deployments. First check staging status and create a rollback plan, then proceed with production deployment. Always ensure safety measures are in place before deploying.",
"DevOpsEngineer",
"DevOps engineer who handles deployments",
ChatClientAgent devopsEngineer = aiProjectClient.AsAIAgent(
model: deploymentName,
instructions: "You are a DevOps engineer responsible for deployments. Call CheckStagingStatus, then CreateRollbackPlan, then DeployToProduction — in that order. Do not ask for confirmation before deploying; deployment approval is handled automatically by the system.",
name: "DevOpsEngineer",
description: "DevOps engineer who handles deployments",
tools:
[
AIFunctionFactory.Create(CheckStagingStatus),
AIFunctionFactory.Create(CreateRollbackPlan),
@@ -75,7 +74,7 @@ public static class Program
// 3. Create custom GroupChatManager with speaker selection logic
DeploymentGroupChatManager manager = new([qaEngineer, devopsEngineer])
{
MaximumIterationCount = 4 // Limit to 4 rounds
MaximumIterationCount = 4
};
// 4. Build a group chat workflow with the custom manager
dotnet/samples/03-workflows/Agents/WorkflowAsAnAgent/Program.cs
+6 -7
View File
@@ -1,6 +1,6 @@
// Copyright (c) Microsoft. All rights reserved.
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Workflows;
@@ -37,13 +37,13 @@ public static class Program
{
private static async Task Main()
{
// Set up the Azure OpenAI client
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var chatClient = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential()).GetChatClient(deploymentName).AsIChatClient();
// Set up the Azure AI Foundry client
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create the workflow and turn it into an agent
var workflow = WorkflowFactory.BuildWorkflow(chatClient);
var workflow = WorkflowFactory.BuildWorkflow(aiProjectClient, deploymentName);
var agent = workflow.AsAIAgent("workflow-agent", "Workflow Agent");
var session = await agent.CreateSessionAsync();
@@ -77,7 +77,6 @@ public static class Program
// skip updates that don't have a message ID or text
continue;
}
Console.Clear();
if (!buffer.TryGetValue(update.MessageId, out List<AgentResponseUpdate>? value))
{
dotnet/samples/03-workflows/Agents/WorkflowAsAnAgent/WorkflowAsAnAgent.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
dotnet/samples/03-workflows/Agents/WorkflowAsAnAgent/WorkflowFactory.cs
+10 -7
View File
@@ -1,5 +1,6 @@
// Copyright (c) Microsoft. All rights reserved.
using Azure.AI.Projects;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Workflows;
using Microsoft.Extensions.AI;
@@ -19,15 +20,16 @@ internal static class WorkflowFactory
/// framework can clear their state between runs. Framework-provided executors like
/// <see cref="ChatForwardingExecutor"/> already implement this interface.
/// </summary>
/// <param name="chatClient">The chat client to use for the agents</param>
/// <param name="client">The AI project client to use for the agents</param>
/// <param name="model">The model deployment name</param>
/// <returns>A workflow that processes input using two language agents</returns>
internal static Workflow BuildWorkflow(IChatClient chatClient)
internal static Workflow BuildWorkflow(AIProjectClient client, string model)
{
// Create executors
var startExecutor = new ChatForwardingExecutor("Start");
var aggregationExecutor = new ConcurrentAggregationExecutor();
AIAgent frenchAgent = GetLanguageAgent("French", chatClient);
AIAgent englishAgent = GetLanguageAgent("English", chatClient);
AIAgent frenchAgent = GetLanguageAgent("French", client, model);
AIAgent englishAgent = GetLanguageAgent("English", client, model);
// Build the workflow by adding executors and connecting them
return new WorkflowBuilder(startExecutor)
@@ -41,10 +43,11 @@ internal static class WorkflowFactory
/// Creates a language agent for the specified target language.
/// </summary>
/// <param name="targetLanguage">The target language for translation</param>
/// <param name="chatClient">The chat client to use for the agent</param>
/// <param name="client">The AI project client to use for the agent</param>
/// <param name="model">The model deployment name</param>
/// <returns>A ChatClientAgent configured for the specified language</returns>
private static ChatClientAgent GetLanguageAgent(string targetLanguage, IChatClient chatClient) =>
new(chatClient, instructions: $"You're a helpful assistant who always responds in {targetLanguage}.", name: $"{targetLanguage}Agent");
private static ChatClientAgent GetLanguageAgent(string targetLanguage, AIProjectClient client, string model) =>
client.AsAIAgent(model: model, instructions: $"You're a helpful assistant who always responds in {targetLanguage}.", name: $"{targetLanguage}Agent");
/// <summary>
/// Executor that aggregates the results from the concurrent agents.
dotnet/samples/03-workflows/ConditionalEdges/01_EdgeCondition/01_EdgeCondition.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
dotnet/samples/03-workflows/ConditionalEdges/01_EdgeCondition/Program.cs
+13 -11
View File
@@ -2,7 +2,7 @@
using System.Text.Json;
using System.Text.Json.Serialization;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Workflows;
@@ -34,14 +34,14 @@ public static class Program
{
private static async Task Main()
{
// Set up the Azure OpenAI client
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var chatClient = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential()).GetChatClient(deploymentName).AsIChatClient();
// Set up the Azure AI Foundry client
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create agents
AIAgent spamDetectionAgent = GetSpamDetectionAgent(chatClient);
AIAgent emailAssistantAgent = GetEmailAssistantAgent(chatClient);
AIAgent spamDetectionAgent = GetSpamDetectionAgent(aiProjectClient, deploymentName);
AIAgent emailAssistantAgent = GetEmailAssistantAgent(aiProjectClient, deploymentName);
// Create executors
var spamDetectionExecutor = new SpamDetectionExecutor(spamDetectionAgent);
@@ -96,11 +96,12 @@ public static class Program
/// Creates a spam detection agent.
/// </summary>
/// <returns>A ChatClientAgent configured for spam detection</returns>
private static ChatClientAgent GetSpamDetectionAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions()
private static ChatClientAgent GetSpamDetectionAgent(AIProjectClient client, string model) =>
client.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new()
{
ModelId = model,
Instructions = "You are a spam detection assistant that identifies spam emails.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<DetectionResult>()
}
@@ -110,11 +111,12 @@ public static class Program
/// Creates an email assistant agent.
/// </summary>
/// <returns>A ChatClientAgent configured for email assistance</returns>
private static ChatClientAgent GetEmailAssistantAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions()
private static ChatClientAgent GetEmailAssistantAgent(AIProjectClient client, string model) =>
client.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new()
{
ModelId = model,
Instructions = "You are an email assistant that helps users draft responses to emails with professionalism.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<EmailResponse>()
}
dotnet/samples/03-workflows/ConditionalEdges/02_SwitchCase/02_SwitchCase.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>
dotnet/samples/03-workflows/ConditionalEdges/02_SwitchCase/Program.cs
+13 -11
View File
@@ -2,7 +2,7 @@
using System.Text.Json;
using System.Text.Json.Serialization;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Workflows;
@@ -35,14 +35,14 @@ public static class Program
{
private static async Task Main()
{
// Set up the Azure OpenAI client
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
var chatClient = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential()).GetChatClient(deploymentName).AsIChatClient();
// Set up the Azure AI Foundry client
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
// Create agents
AIAgent spamDetectionAgent = GetSpamDetectionAgent(chatClient);
AIAgent emailAssistantAgent = GetEmailAssistantAgent(chatClient);
AIAgent spamDetectionAgent = GetSpamDetectionAgent(aiProjectClient, deploymentName);
AIAgent emailAssistantAgent = GetEmailAssistantAgent(aiProjectClient, deploymentName);
// Create executors
var spamDetectionExecutor = new SpamDetectionExecutor(spamDetectionAgent);
@@ -111,11 +111,12 @@ public static class Program
/// Creates a spam detection agent.
/// </summary>
/// <returns>A ChatClientAgent configured for spam detection</returns>
private static ChatClientAgent GetSpamDetectionAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions()
private static ChatClientAgent GetSpamDetectionAgent(AIProjectClient client, string model) =>
client.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new()
{
ModelId = model,
Instructions = "You are a spam detection assistant that identifies spam emails. Be less confident in your assessments.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<DetectionResult>()
}
@@ -125,11 +126,12 @@ public static class Program
/// Creates an email assistant agent.
/// </summary>
/// <returns>A ChatClientAgent configured for email assistance</returns>
private static ChatClientAgent GetEmailAssistantAgent(IChatClient chatClient) =>
new(chatClient, new ChatClientAgentOptions()
private static ChatClientAgent GetEmailAssistantAgent(AIProjectClient client, string model) =>
client.AsAIAgent(new ChatClientAgentOptions()
{
ChatOptions = new()
{
ModelId = model,
Instructions = "You are an email assistant that helps users draft responses to emails with professionalism.",
ResponseFormat = ChatResponseFormat.ForJsonSchema<EmailResponse>()
}
dotnet/samples/03-workflows/ConditionalEdges/03_MultiSelection/03_MultiSelection.csproj
+2 -6
View File
@@ -1,4 +1,4 @@
<Project Sdk="Microsoft.NET.Sdk">
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
@@ -9,12 +9,8 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Azure.AI.OpenAI" />
<PackageReference Include="Azure.Identity" />
<PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
</ItemGroup>
<ItemGroup>
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
<ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
</ItemGroup>

Some files were not shown because too many files have changed in this diff Show More